.
├── [1.8M] data
│ └── [1.8M] bronze
│ ├── [140K] Gemini_BTCUSD_d.csv
│ ├── [117K] Gemini_ETHUSD_d.csv
│ ├── [ 89K] MSFT.csv
│ ├── [520K] rsc.txt
│ ├── [452K] tb.txt
│ ├── [ 87K] TSLA.csv
│ └── [443K] yelp.txt
├── [9.7M] docs
│ ├── [ 472] _config.yml
│ ├── [6.2M] _images
│ ├── [5.9K] L268705_Offline_Reinforcement_Learning.ipynb
│ ├── [ 12K] L732057_Markov_Decision_Process.ipynb
│ ├── [ 38K] R984600_DRL_in_RecSys.ipynb
│ ├── [ 43K] T000348_Multi_armed_Bandit_for_Banner_Ad.ipynb
│ ├── [167K] T035236_MDP_with_Dynamic_Programming_in_PyTorch.ipynb
│ ├── [ 68K] T046728_n_step_algorithms_and_eligibility_traces.ipynb
│ ├── [263K] T079222_Solving_Multi_armed_Bandit_Problems.ipynb
│ ├── [ 26K] T079716_Importance_sampling.ipynb
│ ├── [280K] T119194_Contextual_RL_Product_Recommender.ipynb
│ ├── [138K] T159137_MDP_Basics_with_Inventory_Control.ipynb
│ ├── [ 18K] T163940_FrozenLake_using_Cross_Entropy.ipynb
│ ├── [ 31K] T219174_Recsim_Catalyst.ipynb
│ ├── [154K] T239645_Neural_Interactive_Collaborative_Filtering.ipynb
│ ├── [119K] T256744_Real_Time_Bidding_in_Advertising.ipynb
│ ├── [101K] T257798_Off_Policy_Learning_in_Two_stage_Recommender_Systems.ipynb
│ ├── [ 83K] T294930_Cartpole_in_PyTorch.ipynb
│ ├── [ 64K] T365137_REINFORCE_in_PyTorch.ipynb
│ ├── [ 34K] T373316_Top_K_Off_Policy_Correction_for_a_REINFORCE_Recommender_System.ipynb
│ ├── [290K] T441700_REINFORCE.ipynb
│ ├── [9.6K] T471382_FrozenLake_using_Value_Iteration.ipynb
│ ├── [ 14K] T532530_Predicting_rewards_with_the_state_value_and_action_value_function.ipynb
│ ├── [ 14K] T587798_FrozenLake_using_Q_Learning.ipynb
│ ├── [ 31K] T589782_Code_Driven_Introduction_to_Reinforcement_Learning.ipynb
│ ├── [306K] T616640_Pydeep_Recsys.ipynb
│ ├── [ 85K] T635579_Q_Learning_vs_SARSA_and_Q_Learning_extensions.ipynb
│ ├── [ 19K] T705437_CartPole_using_Cross_Entropy.ipynb
│ ├── [461K] T726861_Introduction_to_Gym_toolkit.ipynb
│ ├── [ 98K] T729495_GAN_User_Model_for_RL_based_Recommendation_System.ipynb
│ ├── [237K] T734685_Deep_Reinforcement_Learning_in_Large_Discrete_Action_Spaces.ipynb
│ ├── [ 49K] T752494_CartPole_using_REINFORCE_in_PyTorch.ipynb
│ ├── [ 27K] T759314_Kullback_Leibler_Divergence.ipynb
│ ├── [111K] T798984_Comparing_Simple_Exploration_Techniques:_ε_Greedy,_Annealing,_and_UCB.ipynb
│ ├── [ 64K] T859183_Q_Learning_on_Lunar_Lander_and_Frozen_Lake.ipynb
│ ├── [ 82K] T985223_Batch_Constrained_Deep_Q_Learning.ipynb
│ └── [1.9K] _toc.yml
├── [ 93K] images
│ └── [ 89K] S990517_process_flow.svg
├── [197K] modules
│ ├── [7.6K] M053518_Builds_a_Gridworld_v2_Environment.ipynb
│ ├── [ 59K] M253973_Builds_Cryptocurrency_Trading_RL_Environment.ipynb
│ ├── [ 55K] M346094_Builds_a_Stock_Trading_RL_Environment.ipynb
│ ├── [ 43K] M445261_Builds_a_Stochastic_Maze_Environment.ipynb
│ ├── [ 12K] M620717_RL_Gridworld_Visualization_Functions.ipynb
│ └── [ 17K] M998022_Builds_a_Gridworld_Environment.ipynb
├── [ 65] README.md
├── [2.8M] reports
│ └── [2.8M] S990517
│ ├── [2.7M] images
│ └── [ 68K] S990517.html
├── [1.7M] tools
│ ├── [ 20K] tradegym.zip
│ └── [1.7M] webgym.zip
└── [5.0M] tutorials
├── [9.5K] T043789_Training_RL_Agent_in_CartPole_Environment_with_Actor_Critic_method.ipynb
├── [343K] T098537_Building_an_RL_Agent_to_manage_social_media_accounts_on_the_web.ipynb
├── [ 23K] T122762_Training_RL_Agent_in_Gridworld_with_Temporal_Difference_learning_method.ipynb
├── [7.6K] T195475_Building_a_simple_Gridworld_v2_Environment.ipynb
├── [216K] T219631_Training_Stock_Trading_RL_Agent_using_SAC_and_Deploying_as_a_Service.ipynb
├── [ 12K] T244614_Training_RL_Agent_in_CartPole_Environment_with_DRQN_method.ipynb
├── [ 62K] T303629_Training_RL_Agent_in_Gridworld_with_Monte_Carlo_Prediction_and_Control_method.ipynb
├── [ 18K] T307891_Training_RL_Agent_in_Mountain_Car_Environment_with_A3C_Continuous_method.ipynb
├── [235K] T344654_Building_Stock_Trading_RL_Environment.ipynb
├── [202K] T350011_Building_Bitcoin_and_Ethereum_Cryptocurrency_based_Trading_RL_Environment.ipynb
├── [ 11K] T432381_Training_RL_Agent_in_CartPole_Environment_with_Dueling_DQN_method.ipynb
├── [ 39K] T453493_Training_RL_Agent_in_Gridworld_with_Q_learning_method.ipynb
├── [126K] T462163_Building_an_RL_Agent_to_book_flights_on_the_web.ipynb
├── [ 15K] T473399_Training_RL_Agent_in_CartPole_Environment_with_DQN_method.ipynb
├── [ 35K] T490651_Training_RL_Agent_in_Gridworld_Environment_with_MLP_Model.ipynb
├── [ 43K] T495794_Building_a_Stochastic_Maze_Gridworld_Environment.ipynb
├── [123K] T515244_Building_an_RL_Agent_to_manage_emails_on_the_web.ipynb
├── [ 42K] T515396_Training_RL_Agent_in_Gridworld_with_SARSA_method.ipynb
├── [ 17K] T533231_Building_a_simple_Gridworld_Environment.ipynb
├── [ 16K] T559464_Training_RL_Agent_in_Pendulum_Environment_with_DDPG_method.ipynb
├── [3.1M] t608854
│ ├── [1.2M] datasets_states
│ │ ├── [ 31K] policyV1.npy
│ │ ├── [ 928] rewardsV1.npy
│ │ └── [1.2M] statesV1.npy
│ ├── [8.1K] eval_baseline.py
│ ├── [100K] eval_results
│ ├── [ 27K] ExpertRecEval.py
│ ├── [1.8K] febr_al_irl.py
│ ├── [9.3K] irl_agent.py
│ ├── [1.0K] LICENSE
│ ├── [8.1K] maxEnt_irl.py
│ ├── [165K] notebooks
│ │ └── [161K] models_eval.ipynb
│ ├── [4.3K] README.md
│ ├── [1.5M] recsim
│ ├── [4.2K] rl.py
│ ├── [5.3K] test1.py
│ ├── [2.4K] test_expertEnv.py
│ ├── [3.6K] test_policyAgent.py
│ └── [5.3K] utils.py
├── [9.2K] T611861_Training_RL_Agent_in_Mountain_Car_Environment_with_Policy_gradient_method.ipynb
├── [ 17K] T626473_Training_RL_Agent_in_Pendulum_Environment_with_PPO_Continuous_method.ipynb
├── [117K] T702798_Building_an_RL_Agent_to_complete_tasks_on_the_web_–_Call_to_Action.ipynb
├── [121K] T769395_Building_an_RL_Agent_to_auto_login_on_the_web.ipynb
├── [ 52K] T778350_Training_an_RL_Agent_for_Trading_Cryptocurrencies_using_SAC_method.ipynb
├── [ 51K] T836251_Training_an_RL_Agent_for_Trading_Stocks_using_SAC_method.ipynb
└── [ 46K] T920001_Training_RL_Agent_in_Maze_Gridworld_with_Value_iteration_method.ipynb
21M used in 25 directories, 218 files
