├── .gitignore ├── README.md ├── rlbook └── ch2-karmedbandit │ ├── K-ArmBandit_example_ver2.2_incremental.html │ ├── K-ArmBandit_example_ver2.2_incremental.ipynb │ ├── index.html │ ├── logo.png │ └── script.js └── session #1 ├── .gitkeep ├── maze_walker_rl_code ├── RL_MazeWalker_Intro.ipynb ├── RL_MazeWalker_Policy_Iteration_Method.ipynb ├── RL_MazeWalker_Value_Iteration_Method.ipynb ├── environment.py ├── policyIteration.py └── valueIteration.py └── presentation └── MLT_RL_Session-1_presentation_20190803.pdf /.gitignore: -------------------------------------------------------------------------------- 1 | .ipynb_checkpoints 2 | __pycache__ 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/README.md -------------------------------------------------------------------------------- /rlbook/ch2-karmedbandit/K-ArmBandit_example_ver2.2_incremental.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/rlbook/ch2-karmedbandit/K-ArmBandit_example_ver2.2_incremental.html -------------------------------------------------------------------------------- /rlbook/ch2-karmedbandit/K-ArmBandit_example_ver2.2_incremental.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/rlbook/ch2-karmedbandit/K-ArmBandit_example_ver2.2_incremental.ipynb -------------------------------------------------------------------------------- /rlbook/ch2-karmedbandit/index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/rlbook/ch2-karmedbandit/index.html -------------------------------------------------------------------------------- /rlbook/ch2-karmedbandit/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/rlbook/ch2-karmedbandit/logo.png -------------------------------------------------------------------------------- /rlbook/ch2-karmedbandit/script.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/rlbook/ch2-karmedbandit/script.js -------------------------------------------------------------------------------- /session #1/.gitkeep: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /session #1/maze_walker_rl_code/RL_MazeWalker_Intro.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/maze_walker_rl_code/RL_MazeWalker_Intro.ipynb -------------------------------------------------------------------------------- /session #1/maze_walker_rl_code/RL_MazeWalker_Policy_Iteration_Method.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/maze_walker_rl_code/RL_MazeWalker_Policy_Iteration_Method.ipynb -------------------------------------------------------------------------------- /session #1/maze_walker_rl_code/RL_MazeWalker_Value_Iteration_Method.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/maze_walker_rl_code/RL_MazeWalker_Value_Iteration_Method.ipynb -------------------------------------------------------------------------------- /session #1/maze_walker_rl_code/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/maze_walker_rl_code/environment.py -------------------------------------------------------------------------------- /session #1/maze_walker_rl_code/policyIteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/maze_walker_rl_code/policyIteration.py -------------------------------------------------------------------------------- /session #1/maze_walker_rl_code/valueIteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/maze_walker_rl_code/valueIteration.py -------------------------------------------------------------------------------- /session #1/presentation/MLT_RL_Session-1_presentation_20190803.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Reinforcement_Learning/HEAD/session #1/presentation/MLT_RL_Session-1_presentation_20190803.pdf --------------------------------------------------------------------------------