【深度強化學習教程】高質量PyTorch實現集錦

【導讀】包含用PyTorch語言編寫的深度強化學習算法的高質量實現。

作者:這些IPython筆記本的目的主要是幫助我練習和理解我讀過的論文;因此,在某些情況下,我將選擇可讀性而不是效率。首先,我會上傳論文的實現,然後是標記來解釋代碼的每一部分。

相關論文


  1. Human Level Control Through Deep Reinforement Learning [Publication] https://deepmind.com/research/publications/human-level-control-through-deep-reinforcement-learning/ [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/01.DQN.ipynb
  2. Multi-Step Learning (from Reinforcement Learning: An Introduction, Chapter 7) [Publication] https://github.com/qfettes/DeepRL-Tutorials/blob/master/01.DQN.ipynb [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/02.NStep_DQN.ipynb
  3. Deep Reinforcement Learning with Double Q-learning [Publication] https://arxiv.org/abs/1509.06461 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/03.Double_DQN.ipynb
  4. Dueling Network Architectures for Deep Reinforcement Learning [Publication] https://arxiv.org/abs/1511.06581 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/04.Dueling_DQN.ipynb
  5. Noisy Networks for Exploration [Publication] https://github.com/qfettes/DeepRL-Tutorials/blob/master/04.Dueling_DQN.ipynb [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/05.DQN-NoisyNets.ipynb
  6. Prioritized Experience Replay [Publication] https://arxiv.org/abs/1511.05952?context=cs [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/06.DQN_PriorityReplay.ipynb
  7. A Distributional Perspective on Reinforcement Learning [Publication] https://arxiv.org/abs/1707.06887 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/07.Categorical-DQN.ipynb
  8. Rainbow: Combining Improvements in Deep Reinforcement Learning [Publication] https://arxiv.org/abs/1710.02298 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/08.Rainbow.ipynb
  9. Distributional Reinforcement Learning with Quantile Regression [Publication] https://arxiv.org/abs/1710.10044 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/09.QuantileRegression-DQN.ipynb
  10. Rainbow with Quantile Regression [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/10.Quantile-Rainbow.ipynb
  11. Deep Recurrent Q-Learning for Partially Observable MDPs [Publication] https://arxiv.org/abs/1507.06527 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/11.DRQN.ipynb
  12. Advantage Actor Critic (A2C) [Publication1] https://arxiv.org/abs/1602.01783 [Publication2] https://blog.openai.com/baselines-acktr-a2c/ [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/12.A2C.ipynb
  13. High-Dimensional Continuous Control Using Generalized Advantage Estimation [Publication] https://arxiv.org/abs/1506.02438 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/13.GAE.ipynb
  14. Proximal Policy Optimization Algorithms [Publication] https://arxiv.org/abs/1707.06347 [code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/14.PPO.ipynb

PyTorch實現


發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章