├── .envrc ├── .github └── workflows │ └── main.yml ├── .gitignore ├── .pycheckers ├── .pylintrc ├── README.md ├── bin ├── alon-style-quotes.lua ├── em-dash-hyphenation.lua ├── remove-hyperref.lua ├── to-pdf └── watch ├── book ├── INDEXING.md ├── README.md ├── abstracts.md ├── appendix1 │ └── appendix1.md ├── appendix2 │ ├── EffFront.png │ └── appendix2.md ├── appendix3 │ └── appendix3.md ├── appendix4 │ └── appendix4.md ├── appendix5 │ └── appendix5.md ├── appendix6 │ └── appendix6.md ├── appendix7 │ └── appendix7.md ├── bibliography │ ├── bibliography.bib │ └── bibliography.md ├── chapter0 │ ├── BabyMDP.jpg │ ├── BranchesOfML.pdf │ ├── CarMDP.jpg │ ├── MDP.png │ ├── ManyFacesOfRL.pdf │ └── chapter0.md ├── chapter1 │ ├── chapter1.md │ └── outline.org ├── chapter10 │ ├── chapter10.md │ ├── dp_backup.png │ ├── mc_backup.png │ ├── mc_td_convergence.png │ ├── memory_function.png │ ├── random_walk_mrp_convergence.png │ ├── td_backup.png │ └── unified_view.png ├── chapter11 │ ├── chapter11.md │ ├── mc_sarsa_convergence.png │ ├── q_learning.gv │ ├── q_learning.png │ ├── sarsa.gv │ ├── sarsa.png │ ├── td.gv │ ├── td.png │ ├── windy_grid_convergence1.png │ └── windy_grid_convergence2.png ├── chapter12 │ ├── chapter12.md │ ├── lstd_vf_comparison.png │ ├── vampire_lspi_opt_policy.png │ ├── vampire_lspi_opt_vf.png │ └── vf_geometry.pdf ├── chapter13 │ ├── chapter13.md │ └── pg_convergence.png ├── chapter14 │ ├── bernoulli_horse_race_arms_count.png │ ├── bernoulli_horse_race_total_regret.png │ ├── chapter14.md │ ├── exp_cum_regret.png │ ├── gaussian_horse_race_arms_count.png │ ├── gaussian_horse_race_total_regret.png │ ├── gradient_bandits_total_regret_curve.png │ ├── q_value_distribution1.png │ ├── q_value_distribution2.png │ ├── total_regret_curves.png │ ├── ts_bernoulli_total_regret_curve.png │ ├── ts_gaussian_total_regret_curve.png │ └── ucb1_total_regret_curve.png ├── chapter15 │ ├── chapter15.md │ ├── learning.gv │ ├── learning.png │ ├── mcts.png │ ├── planning.gv │ ├── planning.png │ ├── planning_learning.gv │ └── planning_learning.png ├── chapter16 │ └── chapter16.md ├── chapter2 │ ├── chapter2.md │ ├── logistic_curves.png │ ├── mrp_bellman_tree.gv │ ├── mrp_bellman_tree.png │ ├── simple_inv_mdp.gv │ ├── simple_inv_mdp.png │ ├── simple_inv_mp.gv │ ├── simple_inv_mp.png │ ├── simple_inv_mrp.gv │ ├── simple_inv_mrp.png │ ├── single_traces.png │ ├── terminal_distribution.png │ ├── unit_sigmoid_curves.png │ ├── weather_mp.gv │ └── weather_mp.png ├── chapter3 │ ├── chapter3.md │ ├── mdp.gv │ ├── mdp.png │ ├── mdp_bellman_opt_tree_qq.gv │ ├── mdp_bellman_opt_tree_qq.png │ ├── mdp_bellman_opt_tree_vv.gv │ ├── mdp_bellman_opt_tree_vv.png │ ├── mdp_bellman_policy_tree_qq.gv │ ├── mdp_bellman_policy_tree_qq.png │ ├── mdp_bellman_policy_tree_vv.gv │ ├── mdp_bellman_policy_tree_vv.png │ ├── pomdp.gv │ └── pomdp.png ├── chapter4 │ ├── chapter4.md │ ├── dynamic_pricing.png │ ├── gpi.png │ ├── policy_iteration_convergence.gv │ ├── policy_iteration_convergence.png │ ├── policy_iteration_loop.gv │ ├── policy_iteration_loop.png │ └── vf_policy_intersecting_lines.png ├── chapter5 │ ├── RMSEForLinearAndDNN.png │ ├── chapter5.md │ └── rmse.png ├── chapter6 │ ├── ce.png │ ├── chapter6.md │ └── utility.png ├── chapter7 │ ├── chapter7.md │ ├── portfolio_growth.png │ └── wealth_trajectory.png ├── chapter8 │ ├── binomial_tree.gv │ ├── binomial_tree.png │ ├── buy_call_option_hedges.png │ ├── chapter8.md │ ├── put_option_ex_boundary.png │ └── sell_call_option_hedges.png ├── chapter9 │ ├── chapter9.md │ ├── order_book.png │ ├── order_book_0.png │ ├── order_book_1.png │ ├── order_book_2.png │ ├── order_book_3.png │ ├── order_book_4.png │ └── order_book_5.png ├── errata │ └── errata.md ├── front_matter.md ├── notation │ └── notation.md └── preface │ └── preface.md ├── default.nix ├── misc ├── index-bold-page-number.png ├── index-page-range.png ├── index-see-also.png ├── index-see.png ├── index-sub-entries.png └── python-workshop │ ├── outline.org │ └── trading_outline.org ├── mypy.ini ├── nix ├── sources.json └── sources.nix ├── notes ├── sampling.org └── td-lambda.org ├── requirements.txt ├── rl ├── __init__.py ├── appendix2 │ └── efficient_frontier.py ├── approximate_dynamic_programming.py ├── chapter1 │ └── probability.py ├── chapter10 │ ├── mc_td_experience_replay.py │ ├── memory_function.py │ ├── prediction_utils.py │ ├── random_walk_mrp.py │ ├── simple_inventory_mrp.py │ ├── simple_inventory_mrp_func_approx.py │ └── test_lambda_return.py ├── chapter11 │ ├── control_utils.py │ ├── simple_inventory_mdp_cap.py │ ├── windy_grid.py │ └── windy_grid_convergence.py ├── chapter12 │ ├── laguerre.py │ ├── optimal_exercise_rl.py │ ├── random_walk_lstd.py │ ├── test_batch_rl_prediction.py │ ├── test_lspi.py │ ├── test_q_learning_experience_replay.py │ └── vampire.py ├── chapter13 │ ├── asset_alloc_pg.py │ └── asset_alloc_reinforce.py ├── chapter14 │ ├── epsilon_greedy.py │ ├── gradient_bandits.py │ ├── mab_base.py │ ├── mab_graphs_gen.py │ ├── plot_mab_graphs.py │ ├── ts_bernoulli.py │ ├── ts_gaussian.py │ └── ucb1.py ├── chapter15 │ └── ams.py ├── chapter2 │ ├── __init__.py │ ├── simple_inventory_mp.py │ ├── simple_inventory_mrp.py │ ├── stock_price_mp.py │ └── stock_price_simulations.py ├── chapter3 │ ├── simple_inventory_mdp_cap.py │ └── simple_inventory_mdp_nocap.py ├── chapter4 │ └── clearance_pricing_mdp.py ├── chapter5 │ ├── func_approx_simple_examples.py │ └── tabular_simple_examples.py ├── chapter7 │ ├── asset_alloc_discrete.py │ └── merton_solution_graph.py ├── chapter8 │ ├── max_exp_utility.py │ ├── optimal_exercise_bi.py │ └── optimal_exercise_bin_tree.py ├── chapter9 │ ├── optimal_order_execution.py │ └── order_book.py ├── distribution.py ├── dynamic_programming.py ├── experience_replay.py ├── finite_horizon.py ├── function_approx.py ├── gen_utils │ ├── __init__.py │ ├── common_funcs.py │ └── plot_funcs.py ├── iterate.py ├── markov_decision_process.py ├── markov_process.py ├── monte_carlo.py ├── policy.py ├── policy_gradient.py ├── problems │ ├── Final-Winter2021 │ │ ├── windy_grid.py │ │ └── windy_grid_outline.py │ └── Midterm-Winter2021 │ │ ├── career_optimization.py │ │ ├── grid_maze.py │ │ ├── midterm-2021-sol1.ipynb │ │ ├── midterm-p1-sol1.ipynb │ │ └── midterm-p1-sol2.ipynb ├── returns.py ├── td.py ├── td_lambda.py ├── test_approx_dp_clearance.py ├── test_approx_dp_inventory.py ├── test_approximate_dynamic_programming.py ├── test_distribution.py ├── test_dynamic_programming.py ├── test_finite_horizon.py ├── test_function_approx.py ├── test_iterate.py ├── test_markov_process.py ├── test_monte_carlo.py └── test_td.py ├── setup.cfg ├── setup.py ├── shell.nix ├── structure ├── templates └── latex.template └── todo.md /.envrc: -------------------------------------------------------------------------------- 1 | eval "$(lorri direnv)" 2 | 3 | -------------------------------------------------------------------------------- /.github/workflows/main.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/.github/workflows/main.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/.gitignore -------------------------------------------------------------------------------- /.pycheckers: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/.pycheckers -------------------------------------------------------------------------------- /.pylintrc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/.pylintrc -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/README.md -------------------------------------------------------------------------------- /bin/alon-style-quotes.lua: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/bin/alon-style-quotes.lua -------------------------------------------------------------------------------- /bin/em-dash-hyphenation.lua: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/bin/em-dash-hyphenation.lua -------------------------------------------------------------------------------- /bin/remove-hyperref.lua: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/bin/remove-hyperref.lua -------------------------------------------------------------------------------- /bin/to-pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/bin/to-pdf -------------------------------------------------------------------------------- /bin/watch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/bin/watch -------------------------------------------------------------------------------- /book/INDEXING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/INDEXING.md -------------------------------------------------------------------------------- /book/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/README.md -------------------------------------------------------------------------------- /book/abstracts.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/abstracts.md -------------------------------------------------------------------------------- /book/appendix1/appendix1.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix1/appendix1.md -------------------------------------------------------------------------------- /book/appendix2/EffFront.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix2/EffFront.png -------------------------------------------------------------------------------- /book/appendix2/appendix2.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix2/appendix2.md -------------------------------------------------------------------------------- /book/appendix3/appendix3.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix3/appendix3.md -------------------------------------------------------------------------------- /book/appendix4/appendix4.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix4/appendix4.md -------------------------------------------------------------------------------- /book/appendix5/appendix5.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix5/appendix5.md -------------------------------------------------------------------------------- /book/appendix6/appendix6.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix6/appendix6.md -------------------------------------------------------------------------------- /book/appendix7/appendix7.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/appendix7/appendix7.md -------------------------------------------------------------------------------- /book/bibliography/bibliography.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/bibliography/bibliography.bib -------------------------------------------------------------------------------- /book/bibliography/bibliography.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/bibliography/bibliography.md -------------------------------------------------------------------------------- /book/chapter0/BabyMDP.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter0/BabyMDP.jpg -------------------------------------------------------------------------------- /book/chapter0/BranchesOfML.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter0/BranchesOfML.pdf -------------------------------------------------------------------------------- /book/chapter0/CarMDP.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter0/CarMDP.jpg -------------------------------------------------------------------------------- /book/chapter0/MDP.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter0/MDP.png -------------------------------------------------------------------------------- /book/chapter0/ManyFacesOfRL.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter0/ManyFacesOfRL.pdf -------------------------------------------------------------------------------- /book/chapter0/chapter0.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter0/chapter0.md -------------------------------------------------------------------------------- /book/chapter1/chapter1.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter1/chapter1.md -------------------------------------------------------------------------------- /book/chapter1/outline.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter1/outline.org -------------------------------------------------------------------------------- /book/chapter10/chapter10.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/chapter10.md -------------------------------------------------------------------------------- /book/chapter10/dp_backup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/dp_backup.png -------------------------------------------------------------------------------- /book/chapter10/mc_backup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/mc_backup.png -------------------------------------------------------------------------------- /book/chapter10/mc_td_convergence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/mc_td_convergence.png -------------------------------------------------------------------------------- /book/chapter10/memory_function.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/memory_function.png -------------------------------------------------------------------------------- /book/chapter10/random_walk_mrp_convergence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/random_walk_mrp_convergence.png -------------------------------------------------------------------------------- /book/chapter10/td_backup.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/td_backup.png -------------------------------------------------------------------------------- /book/chapter10/unified_view.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter10/unified_view.png -------------------------------------------------------------------------------- /book/chapter11/chapter11.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/chapter11.md -------------------------------------------------------------------------------- /book/chapter11/mc_sarsa_convergence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/mc_sarsa_convergence.png -------------------------------------------------------------------------------- /book/chapter11/q_learning.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/q_learning.gv -------------------------------------------------------------------------------- /book/chapter11/q_learning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/q_learning.png -------------------------------------------------------------------------------- /book/chapter11/sarsa.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/sarsa.gv -------------------------------------------------------------------------------- /book/chapter11/sarsa.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/sarsa.png -------------------------------------------------------------------------------- /book/chapter11/td.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/td.gv -------------------------------------------------------------------------------- /book/chapter11/td.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/td.png -------------------------------------------------------------------------------- /book/chapter11/windy_grid_convergence1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/windy_grid_convergence1.png -------------------------------------------------------------------------------- /book/chapter11/windy_grid_convergence2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter11/windy_grid_convergence2.png -------------------------------------------------------------------------------- /book/chapter12/chapter12.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter12/chapter12.md -------------------------------------------------------------------------------- /book/chapter12/lstd_vf_comparison.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter12/lstd_vf_comparison.png -------------------------------------------------------------------------------- /book/chapter12/vampire_lspi_opt_policy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter12/vampire_lspi_opt_policy.png -------------------------------------------------------------------------------- /book/chapter12/vampire_lspi_opt_vf.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter12/vampire_lspi_opt_vf.png -------------------------------------------------------------------------------- /book/chapter12/vf_geometry.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter12/vf_geometry.pdf -------------------------------------------------------------------------------- /book/chapter13/chapter13.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter13/chapter13.md -------------------------------------------------------------------------------- /book/chapter13/pg_convergence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter13/pg_convergence.png -------------------------------------------------------------------------------- /book/chapter14/bernoulli_horse_race_arms_count.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/bernoulli_horse_race_arms_count.png -------------------------------------------------------------------------------- /book/chapter14/bernoulli_horse_race_total_regret.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/bernoulli_horse_race_total_regret.png -------------------------------------------------------------------------------- /book/chapter14/chapter14.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/chapter14.md -------------------------------------------------------------------------------- /book/chapter14/exp_cum_regret.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/exp_cum_regret.png -------------------------------------------------------------------------------- /book/chapter14/gaussian_horse_race_arms_count.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/gaussian_horse_race_arms_count.png -------------------------------------------------------------------------------- /book/chapter14/gaussian_horse_race_total_regret.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/gaussian_horse_race_total_regret.png -------------------------------------------------------------------------------- /book/chapter14/gradient_bandits_total_regret_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/gradient_bandits_total_regret_curve.png -------------------------------------------------------------------------------- /book/chapter14/q_value_distribution1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/q_value_distribution1.png -------------------------------------------------------------------------------- /book/chapter14/q_value_distribution2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/q_value_distribution2.png -------------------------------------------------------------------------------- /book/chapter14/total_regret_curves.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/total_regret_curves.png -------------------------------------------------------------------------------- /book/chapter14/ts_bernoulli_total_regret_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/ts_bernoulli_total_regret_curve.png -------------------------------------------------------------------------------- /book/chapter14/ts_gaussian_total_regret_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/ts_gaussian_total_regret_curve.png -------------------------------------------------------------------------------- /book/chapter14/ucb1_total_regret_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter14/ucb1_total_regret_curve.png -------------------------------------------------------------------------------- /book/chapter15/chapter15.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/chapter15.md -------------------------------------------------------------------------------- /book/chapter15/learning.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/learning.gv -------------------------------------------------------------------------------- /book/chapter15/learning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/learning.png -------------------------------------------------------------------------------- /book/chapter15/mcts.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/mcts.png -------------------------------------------------------------------------------- /book/chapter15/planning.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/planning.gv -------------------------------------------------------------------------------- /book/chapter15/planning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/planning.png -------------------------------------------------------------------------------- /book/chapter15/planning_learning.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/planning_learning.gv -------------------------------------------------------------------------------- /book/chapter15/planning_learning.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter15/planning_learning.png -------------------------------------------------------------------------------- /book/chapter16/chapter16.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter16/chapter16.md -------------------------------------------------------------------------------- /book/chapter2/chapter2.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/chapter2.md -------------------------------------------------------------------------------- /book/chapter2/logistic_curves.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/logistic_curves.png -------------------------------------------------------------------------------- /book/chapter2/mrp_bellman_tree.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/mrp_bellman_tree.gv -------------------------------------------------------------------------------- /book/chapter2/mrp_bellman_tree.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/mrp_bellman_tree.png -------------------------------------------------------------------------------- /book/chapter2/simple_inv_mdp.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/simple_inv_mdp.gv -------------------------------------------------------------------------------- /book/chapter2/simple_inv_mdp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/simple_inv_mdp.png -------------------------------------------------------------------------------- /book/chapter2/simple_inv_mp.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/simple_inv_mp.gv -------------------------------------------------------------------------------- /book/chapter2/simple_inv_mp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/simple_inv_mp.png -------------------------------------------------------------------------------- /book/chapter2/simple_inv_mrp.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/simple_inv_mrp.gv -------------------------------------------------------------------------------- /book/chapter2/simple_inv_mrp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/simple_inv_mrp.png -------------------------------------------------------------------------------- /book/chapter2/single_traces.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/single_traces.png -------------------------------------------------------------------------------- /book/chapter2/terminal_distribution.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/terminal_distribution.png -------------------------------------------------------------------------------- /book/chapter2/unit_sigmoid_curves.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/unit_sigmoid_curves.png -------------------------------------------------------------------------------- /book/chapter2/weather_mp.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/weather_mp.gv -------------------------------------------------------------------------------- /book/chapter2/weather_mp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter2/weather_mp.png -------------------------------------------------------------------------------- /book/chapter3/chapter3.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/chapter3.md -------------------------------------------------------------------------------- /book/chapter3/mdp.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp.gv -------------------------------------------------------------------------------- /book/chapter3/mdp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp.png -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_opt_tree_qq.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_opt_tree_qq.gv -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_opt_tree_qq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_opt_tree_qq.png -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_opt_tree_vv.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_opt_tree_vv.gv -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_opt_tree_vv.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_opt_tree_vv.png -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_policy_tree_qq.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_policy_tree_qq.gv -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_policy_tree_qq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_policy_tree_qq.png -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_policy_tree_vv.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_policy_tree_vv.gv -------------------------------------------------------------------------------- /book/chapter3/mdp_bellman_policy_tree_vv.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/mdp_bellman_policy_tree_vv.png -------------------------------------------------------------------------------- /book/chapter3/pomdp.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/pomdp.gv -------------------------------------------------------------------------------- /book/chapter3/pomdp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter3/pomdp.png -------------------------------------------------------------------------------- /book/chapter4/chapter4.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/chapter4.md -------------------------------------------------------------------------------- /book/chapter4/dynamic_pricing.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/dynamic_pricing.png -------------------------------------------------------------------------------- /book/chapter4/gpi.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/gpi.png -------------------------------------------------------------------------------- /book/chapter4/policy_iteration_convergence.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/policy_iteration_convergence.gv -------------------------------------------------------------------------------- /book/chapter4/policy_iteration_convergence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/policy_iteration_convergence.png -------------------------------------------------------------------------------- /book/chapter4/policy_iteration_loop.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/policy_iteration_loop.gv -------------------------------------------------------------------------------- /book/chapter4/policy_iteration_loop.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/policy_iteration_loop.png -------------------------------------------------------------------------------- /book/chapter4/vf_policy_intersecting_lines.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter4/vf_policy_intersecting_lines.png -------------------------------------------------------------------------------- /book/chapter5/RMSEForLinearAndDNN.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter5/RMSEForLinearAndDNN.png -------------------------------------------------------------------------------- /book/chapter5/chapter5.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter5/chapter5.md -------------------------------------------------------------------------------- /book/chapter5/rmse.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter5/rmse.png -------------------------------------------------------------------------------- /book/chapter6/ce.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter6/ce.png -------------------------------------------------------------------------------- /book/chapter6/chapter6.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter6/chapter6.md -------------------------------------------------------------------------------- /book/chapter6/utility.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter6/utility.png -------------------------------------------------------------------------------- /book/chapter7/chapter7.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter7/chapter7.md -------------------------------------------------------------------------------- /book/chapter7/portfolio_growth.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter7/portfolio_growth.png -------------------------------------------------------------------------------- /book/chapter7/wealth_trajectory.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter7/wealth_trajectory.png -------------------------------------------------------------------------------- /book/chapter8/binomial_tree.gv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter8/binomial_tree.gv -------------------------------------------------------------------------------- /book/chapter8/binomial_tree.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter8/binomial_tree.png -------------------------------------------------------------------------------- /book/chapter8/buy_call_option_hedges.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter8/buy_call_option_hedges.png -------------------------------------------------------------------------------- /book/chapter8/chapter8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter8/chapter8.md -------------------------------------------------------------------------------- /book/chapter8/put_option_ex_boundary.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter8/put_option_ex_boundary.png -------------------------------------------------------------------------------- /book/chapter8/sell_call_option_hedges.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter8/sell_call_option_hedges.png -------------------------------------------------------------------------------- /book/chapter9/chapter9.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/chapter9.md -------------------------------------------------------------------------------- /book/chapter9/order_book.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book.png -------------------------------------------------------------------------------- /book/chapter9/order_book_0.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book_0.png -------------------------------------------------------------------------------- /book/chapter9/order_book_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book_1.png -------------------------------------------------------------------------------- /book/chapter9/order_book_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book_2.png -------------------------------------------------------------------------------- /book/chapter9/order_book_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book_3.png -------------------------------------------------------------------------------- /book/chapter9/order_book_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book_4.png -------------------------------------------------------------------------------- /book/chapter9/order_book_5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/chapter9/order_book_5.png -------------------------------------------------------------------------------- /book/errata/errata.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/errata/errata.md -------------------------------------------------------------------------------- /book/front_matter.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/front_matter.md -------------------------------------------------------------------------------- /book/notation/notation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/notation/notation.md -------------------------------------------------------------------------------- /book/preface/preface.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/book/preface/preface.md -------------------------------------------------------------------------------- /default.nix: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/default.nix -------------------------------------------------------------------------------- /misc/index-bold-page-number.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/index-bold-page-number.png -------------------------------------------------------------------------------- /misc/index-page-range.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/index-page-range.png -------------------------------------------------------------------------------- /misc/index-see-also.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/index-see-also.png -------------------------------------------------------------------------------- /misc/index-see.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/index-see.png -------------------------------------------------------------------------------- /misc/index-sub-entries.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/index-sub-entries.png -------------------------------------------------------------------------------- /misc/python-workshop/outline.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/python-workshop/outline.org -------------------------------------------------------------------------------- /misc/python-workshop/trading_outline.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/misc/python-workshop/trading_outline.org -------------------------------------------------------------------------------- /mypy.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/mypy.ini -------------------------------------------------------------------------------- /nix/sources.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/nix/sources.json -------------------------------------------------------------------------------- /nix/sources.nix: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/nix/sources.nix -------------------------------------------------------------------------------- /notes/sampling.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/notes/sampling.org -------------------------------------------------------------------------------- /notes/td-lambda.org: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/notes/td-lambda.org -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/requirements.txt -------------------------------------------------------------------------------- /rl/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl/appendix2/efficient_frontier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/appendix2/efficient_frontier.py -------------------------------------------------------------------------------- /rl/approximate_dynamic_programming.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/approximate_dynamic_programming.py -------------------------------------------------------------------------------- /rl/chapter1/probability.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter1/probability.py -------------------------------------------------------------------------------- /rl/chapter10/mc_td_experience_replay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/mc_td_experience_replay.py -------------------------------------------------------------------------------- /rl/chapter10/memory_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/memory_function.py -------------------------------------------------------------------------------- /rl/chapter10/prediction_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/prediction_utils.py -------------------------------------------------------------------------------- /rl/chapter10/random_walk_mrp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/random_walk_mrp.py -------------------------------------------------------------------------------- /rl/chapter10/simple_inventory_mrp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/simple_inventory_mrp.py -------------------------------------------------------------------------------- /rl/chapter10/simple_inventory_mrp_func_approx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/simple_inventory_mrp_func_approx.py -------------------------------------------------------------------------------- /rl/chapter10/test_lambda_return.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter10/test_lambda_return.py -------------------------------------------------------------------------------- /rl/chapter11/control_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter11/control_utils.py -------------------------------------------------------------------------------- /rl/chapter11/simple_inventory_mdp_cap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter11/simple_inventory_mdp_cap.py -------------------------------------------------------------------------------- /rl/chapter11/windy_grid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter11/windy_grid.py -------------------------------------------------------------------------------- /rl/chapter11/windy_grid_convergence.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter11/windy_grid_convergence.py -------------------------------------------------------------------------------- /rl/chapter12/laguerre.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter12/laguerre.py -------------------------------------------------------------------------------- /rl/chapter12/optimal_exercise_rl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter12/optimal_exercise_rl.py -------------------------------------------------------------------------------- /rl/chapter12/random_walk_lstd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter12/random_walk_lstd.py -------------------------------------------------------------------------------- /rl/chapter12/test_batch_rl_prediction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter12/test_batch_rl_prediction.py -------------------------------------------------------------------------------- /rl/chapter12/test_lspi.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl/chapter12/test_q_learning_experience_replay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter12/test_q_learning_experience_replay.py -------------------------------------------------------------------------------- /rl/chapter12/vampire.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter12/vampire.py -------------------------------------------------------------------------------- /rl/chapter13/asset_alloc_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter13/asset_alloc_pg.py -------------------------------------------------------------------------------- /rl/chapter13/asset_alloc_reinforce.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter13/asset_alloc_reinforce.py -------------------------------------------------------------------------------- /rl/chapter14/epsilon_greedy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/epsilon_greedy.py -------------------------------------------------------------------------------- /rl/chapter14/gradient_bandits.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/gradient_bandits.py -------------------------------------------------------------------------------- /rl/chapter14/mab_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/mab_base.py -------------------------------------------------------------------------------- /rl/chapter14/mab_graphs_gen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/mab_graphs_gen.py -------------------------------------------------------------------------------- /rl/chapter14/plot_mab_graphs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/plot_mab_graphs.py -------------------------------------------------------------------------------- /rl/chapter14/ts_bernoulli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/ts_bernoulli.py -------------------------------------------------------------------------------- /rl/chapter14/ts_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/ts_gaussian.py -------------------------------------------------------------------------------- /rl/chapter14/ucb1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter14/ucb1.py -------------------------------------------------------------------------------- /rl/chapter15/ams.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter15/ams.py -------------------------------------------------------------------------------- /rl/chapter2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl/chapter2/simple_inventory_mp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter2/simple_inventory_mp.py -------------------------------------------------------------------------------- /rl/chapter2/simple_inventory_mrp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter2/simple_inventory_mrp.py -------------------------------------------------------------------------------- /rl/chapter2/stock_price_mp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter2/stock_price_mp.py -------------------------------------------------------------------------------- /rl/chapter2/stock_price_simulations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter2/stock_price_simulations.py -------------------------------------------------------------------------------- /rl/chapter3/simple_inventory_mdp_cap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter3/simple_inventory_mdp_cap.py -------------------------------------------------------------------------------- /rl/chapter3/simple_inventory_mdp_nocap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter3/simple_inventory_mdp_nocap.py -------------------------------------------------------------------------------- /rl/chapter4/clearance_pricing_mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter4/clearance_pricing_mdp.py -------------------------------------------------------------------------------- /rl/chapter5/func_approx_simple_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter5/func_approx_simple_examples.py -------------------------------------------------------------------------------- /rl/chapter5/tabular_simple_examples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter5/tabular_simple_examples.py -------------------------------------------------------------------------------- /rl/chapter7/asset_alloc_discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter7/asset_alloc_discrete.py -------------------------------------------------------------------------------- /rl/chapter7/merton_solution_graph.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter7/merton_solution_graph.py -------------------------------------------------------------------------------- /rl/chapter8/max_exp_utility.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter8/max_exp_utility.py -------------------------------------------------------------------------------- /rl/chapter8/optimal_exercise_bi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter8/optimal_exercise_bi.py -------------------------------------------------------------------------------- /rl/chapter8/optimal_exercise_bin_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter8/optimal_exercise_bin_tree.py -------------------------------------------------------------------------------- /rl/chapter9/optimal_order_execution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter9/optimal_order_execution.py -------------------------------------------------------------------------------- /rl/chapter9/order_book.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/chapter9/order_book.py -------------------------------------------------------------------------------- /rl/distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/distribution.py -------------------------------------------------------------------------------- /rl/dynamic_programming.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/dynamic_programming.py -------------------------------------------------------------------------------- /rl/experience_replay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/experience_replay.py -------------------------------------------------------------------------------- /rl/finite_horizon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/finite_horizon.py -------------------------------------------------------------------------------- /rl/function_approx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/function_approx.py -------------------------------------------------------------------------------- /rl/gen_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rl/gen_utils/common_funcs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/gen_utils/common_funcs.py -------------------------------------------------------------------------------- /rl/gen_utils/plot_funcs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/gen_utils/plot_funcs.py -------------------------------------------------------------------------------- /rl/iterate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/iterate.py -------------------------------------------------------------------------------- /rl/markov_decision_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/markov_decision_process.py -------------------------------------------------------------------------------- /rl/markov_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/markov_process.py -------------------------------------------------------------------------------- /rl/monte_carlo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/monte_carlo.py -------------------------------------------------------------------------------- /rl/policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/policy.py -------------------------------------------------------------------------------- /rl/policy_gradient.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/policy_gradient.py -------------------------------------------------------------------------------- /rl/problems/Final-Winter2021/windy_grid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Final-Winter2021/windy_grid.py -------------------------------------------------------------------------------- /rl/problems/Final-Winter2021/windy_grid_outline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Final-Winter2021/windy_grid_outline.py -------------------------------------------------------------------------------- /rl/problems/Midterm-Winter2021/career_optimization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Midterm-Winter2021/career_optimization.py -------------------------------------------------------------------------------- /rl/problems/Midterm-Winter2021/grid_maze.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Midterm-Winter2021/grid_maze.py -------------------------------------------------------------------------------- /rl/problems/Midterm-Winter2021/midterm-2021-sol1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Midterm-Winter2021/midterm-2021-sol1.ipynb -------------------------------------------------------------------------------- /rl/problems/Midterm-Winter2021/midterm-p1-sol1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Midterm-Winter2021/midterm-p1-sol1.ipynb -------------------------------------------------------------------------------- /rl/problems/Midterm-Winter2021/midterm-p1-sol2.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/problems/Midterm-Winter2021/midterm-p1-sol2.ipynb -------------------------------------------------------------------------------- /rl/returns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/returns.py -------------------------------------------------------------------------------- /rl/td.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/td.py -------------------------------------------------------------------------------- /rl/td_lambda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/td_lambda.py -------------------------------------------------------------------------------- /rl/test_approx_dp_clearance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_approx_dp_clearance.py -------------------------------------------------------------------------------- /rl/test_approx_dp_inventory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_approx_dp_inventory.py -------------------------------------------------------------------------------- /rl/test_approximate_dynamic_programming.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_approximate_dynamic_programming.py -------------------------------------------------------------------------------- /rl/test_distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_distribution.py -------------------------------------------------------------------------------- /rl/test_dynamic_programming.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_dynamic_programming.py -------------------------------------------------------------------------------- /rl/test_finite_horizon.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_finite_horizon.py -------------------------------------------------------------------------------- /rl/test_function_approx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_function_approx.py -------------------------------------------------------------------------------- /rl/test_iterate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_iterate.py -------------------------------------------------------------------------------- /rl/test_markov_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_markov_process.py -------------------------------------------------------------------------------- /rl/test_monte_carlo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_monte_carlo.py -------------------------------------------------------------------------------- /rl/test_td.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/rl/test_td.py -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/setup.py -------------------------------------------------------------------------------- /shell.nix: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/shell.nix -------------------------------------------------------------------------------- /structure: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/structure -------------------------------------------------------------------------------- /templates/latex.template: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/templates/latex.template -------------------------------------------------------------------------------- /todo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TikhonJelvis/RL-book/HEAD/todo.md --------------------------------------------------------------------------------