├── .gitignore ├── README.md ├── hw1 ├── README.md ├── cs285 │ ├── agents │ │ ├── __init__.py │ │ ├── base_agent.py │ │ └── bc_agent.py │ ├── expert_data │ │ ├── expert_data_Ant-v2.pkl │ │ ├── expert_data_HalfCheetah-v2.pkl │ │ ├── expert_data_Hopper-v2.pkl │ │ ├── expert_data_Humanoid-v2.pkl │ │ └── expert_data_Walker2d-v2.pkl │ ├── infrastructure │ │ ├── __init__.py │ │ ├── colab_utils.py │ │ ├── logger.py │ │ ├── pytorch_util.py │ │ ├── replay_buffer.py │ │ ├── rl_trainer.py │ │ └── utils.py │ ├── policies │ │ ├── MLP_policy.py │ │ ├── __init__.py │ │ ├── base_policy.py │ │ ├── experts │ │ │ ├── Ant.pkl │ │ │ ├── HalfCheetah.pkl │ │ │ ├── Hopper.pkl │ │ │ ├── Humanoid.pkl │ │ │ └── Walker2d.pkl │ │ └── loaded_gaussian_policy.py │ └── scripts │ │ ├── run_hw1.ipynb │ │ └── run_hw1.py ├── cs285_hw1.pdf ├── installation.md ├── requirements.txt ├── requirements_colab.txt └── setup.py ├── hw2 ├── README.md ├── cs285 │ ├── agents │ │ ├── __init__.py │ │ ├── base_agent.py │ │ └── pg_agent.py │ ├── infrastructure │ │ ├── __init__.py │ │ ├── colab_utils.py │ │ ├── logger.py │ │ ├── pytorch_util.py │ │ ├── replay_buffer.py │ │ ├── rl_trainer.py │ │ └── utils.py │ ├── policies │ │ ├── MLP_policy.py │ │ ├── __init__.py │ │ └── base_policy.py │ └── scripts │ │ ├── read_results.py │ │ ├── run_hw2.ipynb │ │ └── run_hw2.py ├── cs285_hw2.pdf ├── requirements.txt ├── requirements_colab.txt └── setup.py ├── hw3 ├── README.md ├── cs285 │ ├── agents │ │ ├── ac_agent.py │ │ ├── base_agent.py │ │ └── dqn_agent.py │ ├── critics │ │ ├── __init__.py │ │ ├── base_critic.py │ │ ├── bootstrapped_continuous_critic.py │ │ └── dqn_critic.py │ ├── envs │ │ ├── __init__.py │ │ └── box2d │ │ │ ├── __init__.py │ │ │ └── lunar_lander.py │ ├── infrastructure │ │ ├── atari_wrappers.py │ │ ├── colab_utils.py │ │ ├── dqn_utils.py │ │ ├── logger.py │ │ ├── pytorch_util.py │ │ ├── replay_buffer.py │ │ ├── rl_trainer.py │ │ └── utils.py │ ├── policies │ │ ├── MLP_policy.py │ │ ├── argmax_policy.py │ │ └── base_policy.py │ └── scripts │ │ ├── read_results.py │ │ ├── run_hw3_actor_critic.ipynb │ │ ├── run_hw3_actor_critic.py │ │ ├── run_hw3_dqn.ipynb │ │ └── run_hw3_dqn.py ├── cs285_hw3.pdf ├── requirements.txt ├── requirements_colab.txt └── setup.py ├── hw4 ├── README.md ├── cs285 │ ├── agents │ │ ├── base_agent.py │ │ └── mb_agent.py │ ├── envs │ │ ├── __init__.py │ │ ├── cheetah │ │ │ ├── __init__.py │ │ │ └── cheetah.py │ │ ├── obstacles │ │ │ ├── __init__.py │ │ │ └── obstacles_env.py │ │ └── reacher │ │ │ ├── __init__.py │ │ │ ├── assets │ │ │ └── sawyer.xml │ │ │ └── reacher_env.py │ ├── infrastructure │ │ ├── colab_utils.py │ │ ├── logger.py │ │ ├── pytorch_util.py │ │ ├── replay_buffer.py │ │ ├── rl_trainer.py │ │ └── utils.py │ ├── models │ │ ├── base_model.py │ │ └── ff_model.py │ ├── policies │ │ ├── MPC_policy.py │ │ └── base_policy.py │ └── scripts │ │ ├── filter_events.py │ │ ├── read_results.py │ │ ├── run_hw4_mb.ipynb │ │ └── run_hw4_mb.py ├── cs285_hw4.pdf ├── requirements.txt ├── requirements_colab.txt └── setup.py └── hw5 ├── README.md ├── cs285 ├── agents │ ├── ac_agent.py │ ├── base_agent.py │ ├── dqn_agent.py │ └── explore_or_exploit_agent.py ├── critics │ ├── __init__.py │ ├── base_critic.py │ ├── bootstrapped_continuous_critic.py │ ├── cql_critic.py │ └── dqn_critic.py ├── envs │ ├── __init__.py │ ├── ant │ │ ├── __init__.py │ │ └── ant.py │ ├── box2d │ │ ├── __init__.py │ │ └── lunar_lander.py │ ├── cheetah │ │ ├── __init__.py │ │ └── cheetah.py │ ├── obstacles │ │ ├── __init__.py │ │ └── obstacles_env.py │ ├── pointmass │ │ └── pointmass.py │ └── reacher │ │ ├── __init__.py │ │ ├── assets │ │ └── sawyer.xml │ │ └── reacher_env.py ├── exploration │ ├── __init__.py │ ├── base_exploration_model.py │ └── rnd_model.py ├── infrastructure │ ├── atari_wrappers.py │ ├── colab_utils.py │ ├── dqn_utils.py │ ├── logger.py │ ├── pytorch_util.py │ ├── replay_buffer.py │ ├── rl_trainer.py │ └── utils.py ├── policies │ ├── MLP_policy.py │ ├── argmax_policy.py │ └── base_policy.py └── scripts │ ├── read_results.py │ └── run_hw5_expl.py ├── hw5.pdf ├── requirements.txt ├── requirements_colab.txt ├── run_hw5_expl.ipynb └── setup.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | data/ -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/README.md -------------------------------------------------------------------------------- /hw1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/README.md -------------------------------------------------------------------------------- /hw1/cs285/agents/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw1/cs285/agents/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/agents/base_agent.py -------------------------------------------------------------------------------- /hw1/cs285/agents/bc_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/agents/bc_agent.py -------------------------------------------------------------------------------- /hw1/cs285/expert_data/expert_data_Ant-v2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/expert_data/expert_data_Ant-v2.pkl -------------------------------------------------------------------------------- /hw1/cs285/expert_data/expert_data_HalfCheetah-v2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/expert_data/expert_data_HalfCheetah-v2.pkl -------------------------------------------------------------------------------- /hw1/cs285/expert_data/expert_data_Hopper-v2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/expert_data/expert_data_Hopper-v2.pkl -------------------------------------------------------------------------------- /hw1/cs285/expert_data/expert_data_Humanoid-v2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/expert_data/expert_data_Humanoid-v2.pkl -------------------------------------------------------------------------------- /hw1/cs285/expert_data/expert_data_Walker2d-v2.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/expert_data/expert_data_Walker2d-v2.pkl -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/colab_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/infrastructure/colab_utils.py -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/infrastructure/logger.py -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/pytorch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/infrastructure/pytorch_util.py -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/infrastructure/replay_buffer.py -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/rl_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/infrastructure/rl_trainer.py -------------------------------------------------------------------------------- /hw1/cs285/infrastructure/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/infrastructure/utils.py -------------------------------------------------------------------------------- /hw1/cs285/policies/MLP_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/MLP_policy.py -------------------------------------------------------------------------------- /hw1/cs285/policies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw1/cs285/policies/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/base_policy.py -------------------------------------------------------------------------------- /hw1/cs285/policies/experts/Ant.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/experts/Ant.pkl -------------------------------------------------------------------------------- /hw1/cs285/policies/experts/HalfCheetah.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/experts/HalfCheetah.pkl -------------------------------------------------------------------------------- /hw1/cs285/policies/experts/Hopper.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/experts/Hopper.pkl -------------------------------------------------------------------------------- /hw1/cs285/policies/experts/Humanoid.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/experts/Humanoid.pkl -------------------------------------------------------------------------------- /hw1/cs285/policies/experts/Walker2d.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/experts/Walker2d.pkl -------------------------------------------------------------------------------- /hw1/cs285/policies/loaded_gaussian_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/policies/loaded_gaussian_policy.py -------------------------------------------------------------------------------- /hw1/cs285/scripts/run_hw1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/scripts/run_hw1.ipynb -------------------------------------------------------------------------------- /hw1/cs285/scripts/run_hw1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285/scripts/run_hw1.py -------------------------------------------------------------------------------- /hw1/cs285_hw1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/cs285_hw1.pdf -------------------------------------------------------------------------------- /hw1/installation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/installation.md -------------------------------------------------------------------------------- /hw1/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/requirements.txt -------------------------------------------------------------------------------- /hw1/requirements_colab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/requirements_colab.txt -------------------------------------------------------------------------------- /hw1/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw1/setup.py -------------------------------------------------------------------------------- /hw2/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/README.md -------------------------------------------------------------------------------- /hw2/cs285/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/agents/__init__.py -------------------------------------------------------------------------------- /hw2/cs285/agents/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/agents/base_agent.py -------------------------------------------------------------------------------- /hw2/cs285/agents/pg_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/agents/pg_agent.py -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/colab_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/infrastructure/colab_utils.py -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/infrastructure/logger.py -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/pytorch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/infrastructure/pytorch_util.py -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/infrastructure/replay_buffer.py -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/rl_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/infrastructure/rl_trainer.py -------------------------------------------------------------------------------- /hw2/cs285/infrastructure/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/infrastructure/utils.py -------------------------------------------------------------------------------- /hw2/cs285/policies/MLP_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/policies/MLP_policy.py -------------------------------------------------------------------------------- /hw2/cs285/policies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw2/cs285/policies/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/policies/base_policy.py -------------------------------------------------------------------------------- /hw2/cs285/scripts/read_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/scripts/read_results.py -------------------------------------------------------------------------------- /hw2/cs285/scripts/run_hw2.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/scripts/run_hw2.ipynb -------------------------------------------------------------------------------- /hw2/cs285/scripts/run_hw2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285/scripts/run_hw2.py -------------------------------------------------------------------------------- /hw2/cs285_hw2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/cs285_hw2.pdf -------------------------------------------------------------------------------- /hw2/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/requirements.txt -------------------------------------------------------------------------------- /hw2/requirements_colab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/requirements_colab.txt -------------------------------------------------------------------------------- /hw2/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw2/setup.py -------------------------------------------------------------------------------- /hw3/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/README.md -------------------------------------------------------------------------------- /hw3/cs285/agents/ac_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/agents/ac_agent.py -------------------------------------------------------------------------------- /hw3/cs285/agents/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/agents/base_agent.py -------------------------------------------------------------------------------- /hw3/cs285/agents/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/agents/dqn_agent.py -------------------------------------------------------------------------------- /hw3/cs285/critics/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /hw3/cs285/critics/base_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/critics/base_critic.py -------------------------------------------------------------------------------- /hw3/cs285/critics/bootstrapped_continuous_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/critics/bootstrapped_continuous_critic.py -------------------------------------------------------------------------------- /hw3/cs285/critics/dqn_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/critics/dqn_critic.py -------------------------------------------------------------------------------- /hw3/cs285/envs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw3/cs285/envs/box2d/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw3/cs285/envs/box2d/lunar_lander.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/envs/box2d/lunar_lander.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/atari_wrappers.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/colab_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/colab_utils.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/dqn_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/dqn_utils.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/logger.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/pytorch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/pytorch_util.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/replay_buffer.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/rl_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/rl_trainer.py -------------------------------------------------------------------------------- /hw3/cs285/infrastructure/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/infrastructure/utils.py -------------------------------------------------------------------------------- /hw3/cs285/policies/MLP_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/policies/MLP_policy.py -------------------------------------------------------------------------------- /hw3/cs285/policies/argmax_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/policies/argmax_policy.py -------------------------------------------------------------------------------- /hw3/cs285/policies/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/policies/base_policy.py -------------------------------------------------------------------------------- /hw3/cs285/scripts/read_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/scripts/read_results.py -------------------------------------------------------------------------------- /hw3/cs285/scripts/run_hw3_actor_critic.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/scripts/run_hw3_actor_critic.ipynb -------------------------------------------------------------------------------- /hw3/cs285/scripts/run_hw3_actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/scripts/run_hw3_actor_critic.py -------------------------------------------------------------------------------- /hw3/cs285/scripts/run_hw3_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/scripts/run_hw3_dqn.ipynb -------------------------------------------------------------------------------- /hw3/cs285/scripts/run_hw3_dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285/scripts/run_hw3_dqn.py -------------------------------------------------------------------------------- /hw3/cs285_hw3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/cs285_hw3.pdf -------------------------------------------------------------------------------- /hw3/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/requirements.txt -------------------------------------------------------------------------------- /hw3/requirements_colab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/requirements_colab.txt -------------------------------------------------------------------------------- /hw3/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw3/setup.py -------------------------------------------------------------------------------- /hw4/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/README.md -------------------------------------------------------------------------------- /hw4/cs285/agents/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/agents/base_agent.py -------------------------------------------------------------------------------- /hw4/cs285/agents/mb_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/agents/mb_agent.py -------------------------------------------------------------------------------- /hw4/cs285/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/__init__.py -------------------------------------------------------------------------------- /hw4/cs285/envs/cheetah/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/cheetah/__init__.py -------------------------------------------------------------------------------- /hw4/cs285/envs/cheetah/cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/cheetah/cheetah.py -------------------------------------------------------------------------------- /hw4/cs285/envs/obstacles/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/obstacles/__init__.py -------------------------------------------------------------------------------- /hw4/cs285/envs/obstacles/obstacles_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/obstacles/obstacles_env.py -------------------------------------------------------------------------------- /hw4/cs285/envs/reacher/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/reacher/__init__.py -------------------------------------------------------------------------------- /hw4/cs285/envs/reacher/assets/sawyer.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/reacher/assets/sawyer.xml -------------------------------------------------------------------------------- /hw4/cs285/envs/reacher/reacher_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/envs/reacher/reacher_env.py -------------------------------------------------------------------------------- /hw4/cs285/infrastructure/colab_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/infrastructure/colab_utils.py -------------------------------------------------------------------------------- /hw4/cs285/infrastructure/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/infrastructure/logger.py -------------------------------------------------------------------------------- /hw4/cs285/infrastructure/pytorch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/infrastructure/pytorch_util.py -------------------------------------------------------------------------------- /hw4/cs285/infrastructure/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/infrastructure/replay_buffer.py -------------------------------------------------------------------------------- /hw4/cs285/infrastructure/rl_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/infrastructure/rl_trainer.py -------------------------------------------------------------------------------- /hw4/cs285/infrastructure/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/infrastructure/utils.py -------------------------------------------------------------------------------- /hw4/cs285/models/base_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/models/base_model.py -------------------------------------------------------------------------------- /hw4/cs285/models/ff_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/models/ff_model.py -------------------------------------------------------------------------------- /hw4/cs285/policies/MPC_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/policies/MPC_policy.py -------------------------------------------------------------------------------- /hw4/cs285/policies/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/policies/base_policy.py -------------------------------------------------------------------------------- /hw4/cs285/scripts/filter_events.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/scripts/filter_events.py -------------------------------------------------------------------------------- /hw4/cs285/scripts/read_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/scripts/read_results.py -------------------------------------------------------------------------------- /hw4/cs285/scripts/run_hw4_mb.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/scripts/run_hw4_mb.ipynb -------------------------------------------------------------------------------- /hw4/cs285/scripts/run_hw4_mb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285/scripts/run_hw4_mb.py -------------------------------------------------------------------------------- /hw4/cs285_hw4.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/cs285_hw4.pdf -------------------------------------------------------------------------------- /hw4/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/requirements.txt -------------------------------------------------------------------------------- /hw4/requirements_colab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/requirements_colab.txt -------------------------------------------------------------------------------- /hw4/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw4/setup.py -------------------------------------------------------------------------------- /hw5/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/README.md -------------------------------------------------------------------------------- /hw5/cs285/agents/ac_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/agents/ac_agent.py -------------------------------------------------------------------------------- /hw5/cs285/agents/base_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/agents/base_agent.py -------------------------------------------------------------------------------- /hw5/cs285/agents/dqn_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/agents/dqn_agent.py -------------------------------------------------------------------------------- /hw5/cs285/agents/explore_or_exploit_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/agents/explore_or_exploit_agent.py -------------------------------------------------------------------------------- /hw5/cs285/critics/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /hw5/cs285/critics/base_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/critics/base_critic.py -------------------------------------------------------------------------------- /hw5/cs285/critics/bootstrapped_continuous_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/critics/bootstrapped_continuous_critic.py -------------------------------------------------------------------------------- /hw5/cs285/critics/cql_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/critics/cql_critic.py -------------------------------------------------------------------------------- /hw5/cs285/critics/dqn_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/critics/dqn_critic.py -------------------------------------------------------------------------------- /hw5/cs285/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/__init__.py -------------------------------------------------------------------------------- /hw5/cs285/envs/ant/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/ant/__init__.py -------------------------------------------------------------------------------- /hw5/cs285/envs/ant/ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/ant/ant.py -------------------------------------------------------------------------------- /hw5/cs285/envs/box2d/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw5/cs285/envs/box2d/lunar_lander.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/box2d/lunar_lander.py -------------------------------------------------------------------------------- /hw5/cs285/envs/cheetah/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/cheetah/__init__.py -------------------------------------------------------------------------------- /hw5/cs285/envs/cheetah/cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/cheetah/cheetah.py -------------------------------------------------------------------------------- /hw5/cs285/envs/obstacles/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/obstacles/__init__.py -------------------------------------------------------------------------------- /hw5/cs285/envs/obstacles/obstacles_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/obstacles/obstacles_env.py -------------------------------------------------------------------------------- /hw5/cs285/envs/pointmass/pointmass.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/pointmass/pointmass.py -------------------------------------------------------------------------------- /hw5/cs285/envs/reacher/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/reacher/__init__.py -------------------------------------------------------------------------------- /hw5/cs285/envs/reacher/assets/sawyer.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/reacher/assets/sawyer.xml -------------------------------------------------------------------------------- /hw5/cs285/envs/reacher/reacher_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/envs/reacher/reacher_env.py -------------------------------------------------------------------------------- /hw5/cs285/exploration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /hw5/cs285/exploration/base_exploration_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/exploration/base_exploration_model.py -------------------------------------------------------------------------------- /hw5/cs285/exploration/rnd_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/exploration/rnd_model.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/atari_wrappers.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/colab_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/colab_utils.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/dqn_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/dqn_utils.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/logger.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/pytorch_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/pytorch_util.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/replay_buffer.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/rl_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/rl_trainer.py -------------------------------------------------------------------------------- /hw5/cs285/infrastructure/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/infrastructure/utils.py -------------------------------------------------------------------------------- /hw5/cs285/policies/MLP_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/policies/MLP_policy.py -------------------------------------------------------------------------------- /hw5/cs285/policies/argmax_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/policies/argmax_policy.py -------------------------------------------------------------------------------- /hw5/cs285/policies/base_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/policies/base_policy.py -------------------------------------------------------------------------------- /hw5/cs285/scripts/read_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/scripts/read_results.py -------------------------------------------------------------------------------- /hw5/cs285/scripts/run_hw5_expl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/cs285/scripts/run_hw5_expl.py -------------------------------------------------------------------------------- /hw5/hw5.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/hw5.pdf -------------------------------------------------------------------------------- /hw5/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/requirements.txt -------------------------------------------------------------------------------- /hw5/requirements_colab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/requirements_colab.txt -------------------------------------------------------------------------------- /hw5/run_hw5_expl.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/run_hw5_expl.ipynb -------------------------------------------------------------------------------- /hw5/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/berkeleydeeprlcourse/homework_fall2020/HEAD/hw5/setup.py --------------------------------------------------------------------------------