赞
踩
本次分享的是用PyTorch语言编写的深度强化学习算法的高质量实现,这些IPython笔记本的目的主要是帮助练习和理解这些论文;因此,在某些情况下,我将选择可读性而不是效率。首先,我会上传论文的实现,然后是标记来解释代码的每一部分。
相关论文
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
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
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
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
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
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
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
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
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
Rainbow with Quantile Regression
[code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/10.Quantile-Rainbow.ipynb
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
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
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
Proximal Policy Optimization Algorithms
[Publication] https://arxiv.org/abs/1707.06347
[code] https://github.com/qfettes/DeepRL-Tutorials/blob/master/14.PPO.ipynb
PyTorch实现
关注公众号,后天回复关键词
20181023
推荐阅读
赛事发布 | 数字合肥广邀智慧城市建设英才,三十万重金等你来战
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。