├── .gitignore ├── Amazon GPU howto.md ├── LICENSE.md ├── README.md ├── docker ├── Dockerfile ├── README.md ├── deeplearning.yaml └── run_jupyter.sh ├── setup_colab.sh ├── week01_intro ├── README.md ├── crossentropy_method.ipynb ├── deep_crossentropy_method.ipynb ├── pong.py ├── primer_python_for_ml │ ├── recap_ml.ipynb │ └── train.csv ├── project_starter_evolution_strategies.ipynb ├── seminar-es-task.ipynb └── seminar_gymnasium_interface.ipynb ├── week02_value_based ├── README.md ├── mdp.py └── seminar_vi.ipynb ├── week03_model_free ├── README.md └── homework.ipynb ├── week04_[recap]_deep_learning ├── README.md ├── mnist.py ├── notmnist.py ├── seminar_pytorch.ipynb └── seminar_tensorflow.ipynb ├── week04_approx_rl ├── README.md ├── dqn │ ├── __init__.py │ ├── analysis.py │ ├── atari_wrappers.py │ ├── logger.py │ ├── replay_buffer.py │ └── utils.py ├── homework_pytorch_debug.ipynb ├── homework_pytorch_main.ipynb ├── homework_tf.ipynb ├── img │ ├── dqn_arch.png │ ├── dueling.png │ ├── dueling_basic.png │ ├── dueling_nature.png │ ├── dueling_single.png │ └── exp_replay.png ├── requirements.txt ├── seminar_pytorch.ipynb ├── seminar_tf.ipynb └── test_td_loss │ └── compute_td_loss.py ├── week05_explore ├── README.md ├── deep_see.png ├── q_learning_agent.py ├── replay_buffer.py ├── und1.mp4 ├── und2.mp4 └── week5.ipynb ├── week06_policy_based ├── README.md ├── a2c-optional.ipynb ├── atari_wrappers.py ├── env_batch.py ├── reinforce_pytorch.ipynb ├── reinforce_tensorflow.ipynb └── runners.py ├── week07_[recap]_rnn ├── README.md ├── arxiv_data.csv ├── mtg_card_names.txt ├── names ├── rnn.png ├── seminar_pytorch.ipynb └── seminar_tf.ipynb ├── week07_seq2seq ├── README.md ├── basic_model_tf.py ├── basic_model_torch.py ├── bonus_pytorch.ipynb ├── he-pron-wiktionary.txt ├── main_dataset.txt ├── practice_tf.ipynb ├── practice_torch.ipynb ├── scheme.svg └── voc.py ├── week08_pomdp ├── README.md ├── atari_util.py ├── env_pool.py ├── img1.jpg ├── img2.jpg ├── img3.jpg ├── practice_pytorch.ipynb └── practice_tensorflow.ipynb ├── week09_policy_II ├── README.md ├── mujoco_wrappers.py ├── ppo.ipynb ├── runners.py ├── seminar_TRPO_pytorch.ipynb ├── seminar_TRPO_tensorflow.ipynb ├── td3_and_sac │ ├── hw-continuous-control_pytorch.ipynb │ └── logger.py └── test_ppo │ ├── actions.npy │ ├── advantages.npy │ ├── log_probs.npy │ ├── observations.npy │ ├── policy │ ├── resets.npy │ ├── rewards.npy │ ├── state.npy │ ├── value_targets.npy │ └── values.npy ├── week10_planning ├── README.md └── seminar_MCTS.ipynb ├── xvfb ├── yet_another_week ├── README.md └── _resource │ ├── README.md │ ├── a3c_scheme.odp │ ├── cliffworld.png │ ├── conv_salary_architecture.odp │ ├── conv_salary_architecture.png │ ├── do_something_scst.png │ ├── dqn_arch.odp │ ├── dqn_arch.png │ ├── env_pool.png │ ├── exp_replay.odp │ ├── exp_replay.png │ ├── msc_2.pdf │ ├── nerd.png │ ├── nnet_arch.odp │ ├── nnet_arch.png │ ├── pca_fish.png │ ├── pomdp_arch.odp │ ├── pomdp_arch.pdf │ ├── pomdp_arch.png │ ├── pomdp_img1.jpg │ ├── pomdp_img2.jpg │ ├── pomdp_img3.jpg │ ├── qlearning_scheme.odp │ ├── qlearning_scheme.pgm │ ├── qlearning_scheme.png │ ├── rollout.png │ ├── scheme.png │ ├── target_net.odp │ ├── target_net.png │ └── training.png └── youtube_dl_lectures.sh /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/.gitignore -------------------------------------------------------------------------------- /Amazon GPU howto.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/Amazon GPU howto.md -------------------------------------------------------------------------------- /LICENSE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/LICENSE.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/README.md -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/docker/Dockerfile -------------------------------------------------------------------------------- /docker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/docker/README.md -------------------------------------------------------------------------------- /docker/deeplearning.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/docker/deeplearning.yaml -------------------------------------------------------------------------------- /docker/run_jupyter.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/docker/run_jupyter.sh -------------------------------------------------------------------------------- /setup_colab.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/setup_colab.sh -------------------------------------------------------------------------------- /week01_intro/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/README.md -------------------------------------------------------------------------------- /week01_intro/crossentropy_method.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/crossentropy_method.ipynb -------------------------------------------------------------------------------- /week01_intro/deep_crossentropy_method.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/deep_crossentropy_method.ipynb -------------------------------------------------------------------------------- /week01_intro/pong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/pong.py -------------------------------------------------------------------------------- /week01_intro/primer_python_for_ml/recap_ml.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/primer_python_for_ml/recap_ml.ipynb -------------------------------------------------------------------------------- /week01_intro/primer_python_for_ml/train.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/primer_python_for_ml/train.csv -------------------------------------------------------------------------------- /week01_intro/project_starter_evolution_strategies.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/project_starter_evolution_strategies.ipynb -------------------------------------------------------------------------------- /week01_intro/seminar-es-task.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/seminar-es-task.ipynb -------------------------------------------------------------------------------- /week01_intro/seminar_gymnasium_interface.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week01_intro/seminar_gymnasium_interface.ipynb -------------------------------------------------------------------------------- /week02_value_based/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week02_value_based/README.md -------------------------------------------------------------------------------- /week02_value_based/mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week02_value_based/mdp.py -------------------------------------------------------------------------------- /week02_value_based/seminar_vi.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week02_value_based/seminar_vi.ipynb -------------------------------------------------------------------------------- /week03_model_free/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week03_model_free/README.md -------------------------------------------------------------------------------- /week03_model_free/homework.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week03_model_free/homework.ipynb -------------------------------------------------------------------------------- /week04_[recap]_deep_learning/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_[recap]_deep_learning/README.md -------------------------------------------------------------------------------- /week04_[recap]_deep_learning/mnist.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_[recap]_deep_learning/mnist.py -------------------------------------------------------------------------------- /week04_[recap]_deep_learning/notmnist.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_[recap]_deep_learning/notmnist.py -------------------------------------------------------------------------------- /week04_[recap]_deep_learning/seminar_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_[recap]_deep_learning/seminar_pytorch.ipynb -------------------------------------------------------------------------------- /week04_[recap]_deep_learning/seminar_tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_[recap]_deep_learning/seminar_tensorflow.ipynb -------------------------------------------------------------------------------- /week04_approx_rl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/README.md -------------------------------------------------------------------------------- /week04_approx_rl/dqn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /week04_approx_rl/dqn/analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/dqn/analysis.py -------------------------------------------------------------------------------- /week04_approx_rl/dqn/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/dqn/atari_wrappers.py -------------------------------------------------------------------------------- /week04_approx_rl/dqn/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/dqn/logger.py -------------------------------------------------------------------------------- /week04_approx_rl/dqn/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/dqn/replay_buffer.py -------------------------------------------------------------------------------- /week04_approx_rl/dqn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/dqn/utils.py -------------------------------------------------------------------------------- /week04_approx_rl/homework_pytorch_debug.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/homework_pytorch_debug.ipynb -------------------------------------------------------------------------------- /week04_approx_rl/homework_pytorch_main.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/homework_pytorch_main.ipynb -------------------------------------------------------------------------------- /week04_approx_rl/homework_tf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/homework_tf.ipynb -------------------------------------------------------------------------------- /week04_approx_rl/img/dqn_arch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/img/dqn_arch.png -------------------------------------------------------------------------------- /week04_approx_rl/img/dueling.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/img/dueling.png -------------------------------------------------------------------------------- /week04_approx_rl/img/dueling_basic.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/img/dueling_basic.png -------------------------------------------------------------------------------- /week04_approx_rl/img/dueling_nature.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/img/dueling_nature.png -------------------------------------------------------------------------------- /week04_approx_rl/img/dueling_single.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/img/dueling_single.png -------------------------------------------------------------------------------- /week04_approx_rl/img/exp_replay.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/img/exp_replay.png -------------------------------------------------------------------------------- /week04_approx_rl/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/requirements.txt -------------------------------------------------------------------------------- /week04_approx_rl/seminar_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/seminar_pytorch.ipynb -------------------------------------------------------------------------------- /week04_approx_rl/seminar_tf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/seminar_tf.ipynb -------------------------------------------------------------------------------- /week04_approx_rl/test_td_loss/compute_td_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week04_approx_rl/test_td_loss/compute_td_loss.py -------------------------------------------------------------------------------- /week05_explore/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/README.md -------------------------------------------------------------------------------- /week05_explore/deep_see.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/deep_see.png -------------------------------------------------------------------------------- /week05_explore/q_learning_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/q_learning_agent.py -------------------------------------------------------------------------------- /week05_explore/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/replay_buffer.py -------------------------------------------------------------------------------- /week05_explore/und1.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/und1.mp4 -------------------------------------------------------------------------------- /week05_explore/und2.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/und2.mp4 -------------------------------------------------------------------------------- /week05_explore/week5.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week05_explore/week5.ipynb -------------------------------------------------------------------------------- /week06_policy_based/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/README.md -------------------------------------------------------------------------------- /week06_policy_based/a2c-optional.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/a2c-optional.ipynb -------------------------------------------------------------------------------- /week06_policy_based/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/atari_wrappers.py -------------------------------------------------------------------------------- /week06_policy_based/env_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/env_batch.py -------------------------------------------------------------------------------- /week06_policy_based/reinforce_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/reinforce_pytorch.ipynb -------------------------------------------------------------------------------- /week06_policy_based/reinforce_tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/reinforce_tensorflow.ipynb -------------------------------------------------------------------------------- /week06_policy_based/runners.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week06_policy_based/runners.py -------------------------------------------------------------------------------- /week07_[recap]_rnn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/README.md -------------------------------------------------------------------------------- /week07_[recap]_rnn/arxiv_data.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/arxiv_data.csv -------------------------------------------------------------------------------- /week07_[recap]_rnn/mtg_card_names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/mtg_card_names.txt -------------------------------------------------------------------------------- /week07_[recap]_rnn/names: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/names -------------------------------------------------------------------------------- /week07_[recap]_rnn/rnn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/rnn.png -------------------------------------------------------------------------------- /week07_[recap]_rnn/seminar_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/seminar_pytorch.ipynb -------------------------------------------------------------------------------- /week07_[recap]_rnn/seminar_tf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_[recap]_rnn/seminar_tf.ipynb -------------------------------------------------------------------------------- /week07_seq2seq/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/README.md -------------------------------------------------------------------------------- /week07_seq2seq/basic_model_tf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/basic_model_tf.py -------------------------------------------------------------------------------- /week07_seq2seq/basic_model_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/basic_model_torch.py -------------------------------------------------------------------------------- /week07_seq2seq/bonus_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/bonus_pytorch.ipynb -------------------------------------------------------------------------------- /week07_seq2seq/he-pron-wiktionary.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/he-pron-wiktionary.txt -------------------------------------------------------------------------------- /week07_seq2seq/main_dataset.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/main_dataset.txt -------------------------------------------------------------------------------- /week07_seq2seq/practice_tf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/practice_tf.ipynb -------------------------------------------------------------------------------- /week07_seq2seq/practice_torch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/practice_torch.ipynb -------------------------------------------------------------------------------- /week07_seq2seq/scheme.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/scheme.svg -------------------------------------------------------------------------------- /week07_seq2seq/voc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week07_seq2seq/voc.py -------------------------------------------------------------------------------- /week08_pomdp/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/README.md -------------------------------------------------------------------------------- /week08_pomdp/atari_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/atari_util.py -------------------------------------------------------------------------------- /week08_pomdp/env_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/env_pool.py -------------------------------------------------------------------------------- /week08_pomdp/img1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/img1.jpg -------------------------------------------------------------------------------- /week08_pomdp/img2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/img2.jpg -------------------------------------------------------------------------------- /week08_pomdp/img3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/img3.jpg -------------------------------------------------------------------------------- /week08_pomdp/practice_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/practice_pytorch.ipynb -------------------------------------------------------------------------------- /week08_pomdp/practice_tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week08_pomdp/practice_tensorflow.ipynb -------------------------------------------------------------------------------- /week09_policy_II/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/README.md -------------------------------------------------------------------------------- /week09_policy_II/mujoco_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/mujoco_wrappers.py -------------------------------------------------------------------------------- /week09_policy_II/ppo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/ppo.ipynb -------------------------------------------------------------------------------- /week09_policy_II/runners.py: -------------------------------------------------------------------------------- 1 | ../week06_policy_based/runners.py -------------------------------------------------------------------------------- /week09_policy_II/seminar_TRPO_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/seminar_TRPO_pytorch.ipynb -------------------------------------------------------------------------------- /week09_policy_II/seminar_TRPO_tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/seminar_TRPO_tensorflow.ipynb -------------------------------------------------------------------------------- /week09_policy_II/td3_and_sac/hw-continuous-control_pytorch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/td3_and_sac/hw-continuous-control_pytorch.ipynb -------------------------------------------------------------------------------- /week09_policy_II/td3_and_sac/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/td3_and_sac/logger.py -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/actions.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/actions.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/advantages.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/advantages.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/log_probs.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/log_probs.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/observations.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/observations.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/policy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/policy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/resets.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/resets.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/rewards.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/rewards.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/state.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/state.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/value_targets.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/value_targets.npy -------------------------------------------------------------------------------- /week09_policy_II/test_ppo/values.npy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week09_policy_II/test_ppo/values.npy -------------------------------------------------------------------------------- /week10_planning/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week10_planning/README.md -------------------------------------------------------------------------------- /week10_planning/seminar_MCTS.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/week10_planning/seminar_MCTS.ipynb -------------------------------------------------------------------------------- /xvfb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/xvfb -------------------------------------------------------------------------------- /yet_another_week/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/README.md -------------------------------------------------------------------------------- /yet_another_week/_resource/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/README.md -------------------------------------------------------------------------------- /yet_another_week/_resource/a3c_scheme.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/a3c_scheme.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/cliffworld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/cliffworld.png -------------------------------------------------------------------------------- /yet_another_week/_resource/conv_salary_architecture.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/conv_salary_architecture.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/conv_salary_architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/conv_salary_architecture.png -------------------------------------------------------------------------------- /yet_another_week/_resource/do_something_scst.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/do_something_scst.png -------------------------------------------------------------------------------- /yet_another_week/_resource/dqn_arch.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/dqn_arch.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/dqn_arch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/dqn_arch.png -------------------------------------------------------------------------------- /yet_another_week/_resource/env_pool.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/env_pool.png -------------------------------------------------------------------------------- /yet_another_week/_resource/exp_replay.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/exp_replay.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/exp_replay.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/exp_replay.png -------------------------------------------------------------------------------- /yet_another_week/_resource/msc_2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/msc_2.pdf -------------------------------------------------------------------------------- /yet_another_week/_resource/nerd.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/nerd.png -------------------------------------------------------------------------------- /yet_another_week/_resource/nnet_arch.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/nnet_arch.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/nnet_arch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/nnet_arch.png -------------------------------------------------------------------------------- /yet_another_week/_resource/pca_fish.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pca_fish.png -------------------------------------------------------------------------------- /yet_another_week/_resource/pomdp_arch.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pomdp_arch.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/pomdp_arch.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pomdp_arch.pdf -------------------------------------------------------------------------------- /yet_another_week/_resource/pomdp_arch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pomdp_arch.png -------------------------------------------------------------------------------- /yet_another_week/_resource/pomdp_img1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pomdp_img1.jpg -------------------------------------------------------------------------------- /yet_another_week/_resource/pomdp_img2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pomdp_img2.jpg -------------------------------------------------------------------------------- /yet_another_week/_resource/pomdp_img3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/pomdp_img3.jpg -------------------------------------------------------------------------------- /yet_another_week/_resource/qlearning_scheme.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/qlearning_scheme.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/qlearning_scheme.pgm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/qlearning_scheme.pgm -------------------------------------------------------------------------------- /yet_another_week/_resource/qlearning_scheme.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/qlearning_scheme.png -------------------------------------------------------------------------------- /yet_another_week/_resource/rollout.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/rollout.png -------------------------------------------------------------------------------- /yet_another_week/_resource/scheme.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/scheme.png -------------------------------------------------------------------------------- /yet_another_week/_resource/target_net.odp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/target_net.odp -------------------------------------------------------------------------------- /yet_another_week/_resource/target_net.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/target_net.png -------------------------------------------------------------------------------- /yet_another_week/_resource/training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/yet_another_week/_resource/training.png -------------------------------------------------------------------------------- /youtube_dl_lectures.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yandexdataschool/Practical_RL/HEAD/youtube_dl_lectures.sh --------------------------------------------------------------------------------