├── .gitignore ├── LICENSE ├── README.md ├── assignment1_coding ├── Makefile ├── collect_submission.sh ├── discrete_env.py ├── frozen_lake.py ├── lake_envs.py ├── requirements.txt └── vi_and_pi.py ├── assignment1_written ├── assignment1.pdf ├── assignment1.tex └── tex │ ├── Q_Grid.tex │ ├── Q_fixedpoint.tex │ ├── Q_policies.tex │ └── grid.png ├── assignment2_coding └── starter_code │ ├── .gitignore │ ├── Makefile │ ├── README.md │ ├── collect_submission.sh │ ├── configs │ ├── __init__.py │ ├── np_linear.py │ ├── q2_linear.py │ ├── q3_nature.py │ ├── q4_train_atari_linear.py │ ├── q5_train_atari_nature.py │ ├── q6_bonus_question.py │ └── test.py │ ├── core │ ├── __init__.py │ ├── deep_q_learning.py │ └── q_learning.py │ ├── q1_schedule.py │ ├── q2_linear.py │ ├── q3_nature.py │ ├── q4_train_atari_linear.py │ ├── q5_train_atari_nature.py │ ├── requirements.txt │ └── utils │ ├── __init__.py │ ├── general.py │ ├── preprocess.py │ ├── replay_buffer.py │ ├── test_env.py │ ├── test_env_old.py │ ├── viewer.py │ └── wrappers.py ├── assignment2_written ├── assignment2.pdf └── handout │ ├── img │ ├── Avg_R.png │ ├── Eval_R.png │ ├── Max_Q.png │ ├── Max_R.png │ ├── pong.jpg │ ├── pong_grey.png │ ├── q2_scores.png │ ├── q3_scores.png │ ├── scores.png │ └── test_env.png │ ├── main-blx.bib │ ├── main.bbl │ ├── main.run.xml │ ├── main.tex │ ├── papers.bib │ └── style.sty ├── assignment3_coding └── starter_code 2 │ ├── Makefile │ ├── code │ ├── __init__.py │ ├── baseline_network.py │ ├── config.py │ ├── general.py │ ├── main.py │ ├── network_utils.py │ ├── plot.py │ └── policy_network.py │ ├── collect_submission.sh │ ├── mujoco_instructions.txt │ ├── requirements.txt │ ├── run_basic_tests.py │ └── tests │ └── test_basic.py └── assignment3_written ├── assignment3.bcf ├── assignment3.pdf ├── assignment3.run.xml └── assignment3.tex /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/README.md -------------------------------------------------------------------------------- /assignment1_coding/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_coding/Makefile -------------------------------------------------------------------------------- /assignment1_coding/collect_submission.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_coding/collect_submission.sh -------------------------------------------------------------------------------- /assignment1_coding/discrete_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_coding/discrete_env.py -------------------------------------------------------------------------------- /assignment1_coding/frozen_lake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_coding/frozen_lake.py -------------------------------------------------------------------------------- /assignment1_coding/lake_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_coding/lake_envs.py -------------------------------------------------------------------------------- /assignment1_coding/requirements.txt: -------------------------------------------------------------------------------- 1 | gym==0.10.9 2 | matplotlib 3 | numpy 4 | scipy 5 | -------------------------------------------------------------------------------- /assignment1_coding/vi_and_pi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_coding/vi_and_pi.py -------------------------------------------------------------------------------- /assignment1_written/assignment1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_written/assignment1.pdf -------------------------------------------------------------------------------- /assignment1_written/assignment1.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_written/assignment1.tex -------------------------------------------------------------------------------- /assignment1_written/tex/Q_Grid.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_written/tex/Q_Grid.tex -------------------------------------------------------------------------------- /assignment1_written/tex/Q_fixedpoint.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_written/tex/Q_fixedpoint.tex -------------------------------------------------------------------------------- /assignment1_written/tex/Q_policies.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_written/tex/Q_policies.tex -------------------------------------------------------------------------------- /assignment1_written/tex/grid.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment1_written/tex/grid.png -------------------------------------------------------------------------------- /assignment2_coding/starter_code/.gitignore: -------------------------------------------------------------------------------- 1 | /results -------------------------------------------------------------------------------- /assignment2_coding/starter_code/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/Makefile -------------------------------------------------------------------------------- /assignment2_coding/starter_code/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/README.md -------------------------------------------------------------------------------- /assignment2_coding/starter_code/collect_submission.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/collect_submission.sh -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/np_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/np_linear.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/q2_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/q2_linear.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/q3_nature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/q3_nature.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/q4_train_atari_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/q4_train_atari_linear.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/q5_train_atari_nature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/q5_train_atari_nature.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/q6_bonus_question.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/q6_bonus_question.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/configs/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/configs/test.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/core/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /assignment2_coding/starter_code/core/deep_q_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/core/deep_q_learning.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/core/q_learning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/core/q_learning.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/q1_schedule.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/q1_schedule.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/q2_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/q2_linear.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/q3_nature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/q3_nature.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/q4_train_atari_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/q4_train_atari_linear.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/q5_train_atari_nature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/q5_train_atari_nature.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/requirements.txt -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/general.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/preprocess.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/replay_buffer.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/test_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/test_env.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/test_env_old.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/test_env_old.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/viewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/viewer.py -------------------------------------------------------------------------------- /assignment2_coding/starter_code/utils/wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_coding/starter_code/utils/wrappers.py -------------------------------------------------------------------------------- /assignment2_written/assignment2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/assignment2.pdf -------------------------------------------------------------------------------- /assignment2_written/handout/img/Avg_R.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/Avg_R.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/Eval_R.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/Eval_R.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/Max_Q.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/Max_Q.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/Max_R.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/Max_R.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/pong.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/pong.jpg -------------------------------------------------------------------------------- /assignment2_written/handout/img/pong_grey.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/pong_grey.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/q2_scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/q2_scores.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/q3_scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/q3_scores.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/scores.png -------------------------------------------------------------------------------- /assignment2_written/handout/img/test_env.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/img/test_env.png -------------------------------------------------------------------------------- /assignment2_written/handout/main-blx.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/main-blx.bib -------------------------------------------------------------------------------- /assignment2_written/handout/main.bbl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/main.bbl -------------------------------------------------------------------------------- /assignment2_written/handout/main.run.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/main.run.xml -------------------------------------------------------------------------------- /assignment2_written/handout/main.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/main.tex -------------------------------------------------------------------------------- /assignment2_written/handout/papers.bib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/papers.bib -------------------------------------------------------------------------------- /assignment2_written/handout/style.sty: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment2_written/handout/style.sty -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/Makefile -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/baseline_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/baseline_network.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/config.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/general.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/main.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/network_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/network_utils.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/plot.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/code/policy_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/code/policy_network.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/collect_submission.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/collect_submission.sh -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/mujoco_instructions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/mujoco_instructions.txt -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/requirements.txt -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/run_basic_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/run_basic_tests.py -------------------------------------------------------------------------------- /assignment3_coding/starter_code 2/tests/test_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_coding/starter_code 2/tests/test_basic.py -------------------------------------------------------------------------------- /assignment3_written/assignment3.bcf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_written/assignment3.bcf -------------------------------------------------------------------------------- /assignment3_written/assignment3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_written/assignment3.pdf -------------------------------------------------------------------------------- /assignment3_written/assignment3.run.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_written/assignment3.run.xml -------------------------------------------------------------------------------- /assignment3_written/assignment3.tex: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ksang/cs234-assignments/HEAD/assignment3_written/assignment3.tex --------------------------------------------------------------------------------