docs/source/api/environments/genrl.environments.vec_env.rst | |
|
|
docs/source/api/environments/index.rst | |
|
|
docs/source/api/trainers/index.rst | |
|
|
docs/source/api/utils/index.rst | |
|
|
docs/source/assets/images/genrl.png | |
|
|
docs/source/assets/images/genrl_cropped.png | |
|
|
docs/source/conf.py | 48 | A 0 mins |
|
docs/source/index.rst | |
|
|
docs/source/usage/about/about.rst | |
|
|
docs/source/usage/about/index.rst | |
|
|
docs/source/usage/tutorials/Classical/Q_Learning.rst | |
|
|
docs/source/usage/tutorials/Classical/Sarsa.rst | |
|
|
docs/source/usage/tutorials/Classical/index.rst | |
|
|
docs/source/usage/tutorials/Deep/A2C.rst | |
|
|
docs/source/usage/tutorials/Deep/Background.rst | |
|
|
docs/source/usage/tutorials/Deep/Categorical_DQN.rst | |
|
|
docs/source/usage/tutorials/Deep/DDPG.rst | |
|
|
docs/source/usage/tutorials/Deep/DQN.rst | |
|
|
docs/source/usage/tutorials/Deep/Double_DQN.rst | |
|
|
docs/source/usage/tutorials/Deep/Dueling_DQN.rst | |
|
|
docs/source/usage/tutorials/Deep/NoisyNet_DQN.rst | |
|
|
docs/source/usage/tutorials/Deep/PPO.rst | |
|
|
docs/source/usage/tutorials/Deep/Prioritized_DQN.rst | |
|
|
docs/source/usage/tutorials/Deep/SAC.rst | |
|
|
docs/source/usage/tutorials/Deep/TD3.rst | |
|
|
docs/source/usage/tutorials/Deep/VPG.rst | |
|
|
docs/source/usage/tutorials/Deep/index.rst | |
|
|
docs/source/usage/tutorials/Deep/static/Categorical_DQN.png | |
|
|
docs/source/usage/tutorials/Saving and loading.rst | |
|
|
docs/source/usage/tutorials/Using A2C.md | |
|
|
docs/source/usage/tutorials/Using Custom Policies.md | |
|
|
docs/source/usage/tutorials/Using shared parameters in actor critic agents.rst | |
|
|
docs/source/usage/tutorials/bandit/adding_data_bandit.rst | |
|
|
docs/source/usage/tutorials/bandit/adding_dcb_agent.rst | |
|
|
docs/source/usage/tutorials/bandit/bandit_overview.rst | |
|
|
docs/source/usage/tutorials/bandit/bayesian.rst | |
|
|
docs/source/usage/tutorials/bandit/bootstrap.rst | |
|
|
docs/source/usage/tutorials/bandit/contextual_overview.rst | |
|
|
docs/source/usage/tutorials/bandit/gradients.rst | |
|
|
docs/source/usage/tutorials/bandit/index.rst | |
|
|
docs/source/usage/tutorials/bandit/linpos.rst | |
|
|
docs/source/usage/tutorials/bandit/noise.rst | |
|
|
docs/source/usage/tutorials/bandit/thompson_sampling.rst | |
|
|
docs/source/usage/tutorials/bandit/ucb.rst | |
|
|
docs/source/usage/tutorials/bandit/variational.rst | |
|
|
docs/source/usage/tutorials/index.rst | |
|
|
docs/source/usage/tutorials/using_vpg.md | |
|
|
environment.yml | |
|
|
examples/Bandit_demo.ipynb | |
|
|
examples/DQN_demo.ipynb | |
|
|