DRL-Tutorial

Related Repos

• Baseline by OpenAI
• Agnets by Tensorflow
• Tianshou by Tsinghua Machine Learning Group

Useful Tools

• Papers with Code

Summarize

Algorithm	Authors	Publication	Code	Classification	Features	Detailed
Markov Decision Processes (MDP)	Puterman, M.L	John Wiley & Sons 2014	/	Model	/	TBD
Temporal Difference (TD) Learning	Tesauro, G.	Communications of the ACM 1995	/	Cornerstone	TBD	TBD
Q-Learning	Watkins, C. J. et al.	Machine Learning 1992	/	/	Q Table	TBD
Deep Q-Networks (DQN)	Mnih, V. et al.	Nature 2015	PyTorch	Q Networks	Deep network + Q-learning	TBD
Deep Deterministic Policy Gradient (DDPG)	Lillicrap, T.P. et al.	arXiv 2015	TBD	AC	Continuous control	TBD
Trust Region Policy Optimization (TRPO)	Schulman, J. et al.	ICML 2015	TBD	Policy	TBD	TBD
Prioritized Experience Replay (PER)	Schaul, T. et al.	arXiv 2015	TBD	Replay	TBD	TBD
Deep Recurrent Q-Network (DRQN)	Hausknecht, M. et al.	AAAI 2015	TBD	Q Networks	TBD	TBD
Monte-Carlo Tree Search (MCTS)	Silver, D. et al.	Nature 2016	TBD	TBD	TBD	TBD
Double DQN	Van Hasselt, H. et al.	AAAI 2016	TBD	Q Networks	TBD	TBD
Dueling DQN	Wang, Z. et al.	ICML 2016	TBD	Q Networks	TBD	TBD
Asynchronous Advantage Actor-Critic (A3C)	Mnih, V. et al.	ICML 2016	TBD	AC	TBD	TBD
Noise Networks	Fortunato, M. et al.	arXiv 2017	TBD	Exploration	TBD	TBD
Hindsight Experience Replay (HER)	Andrychowicz, M. et al.	NeurIPS 2017	TBD	Replay	TBD	TBD
Soft Q-Learning (SQL)	Haarnoja, T. et al.	ICML 2017	TBD	TBD	TBD	TBD
Distributional DQN	Bellemare, M.G. et al.	ICML 2017	TBD	Q Networks	TBD	TBD
Proximal Policy Optimization (PPO)	Schulman, J. et al.	arXiv 2017	TBD	Policy	TBD	TBD
Multi-Agent DDPG (MADDPG)	Lowe, R. et al.	NeurIPS 2017	TBD	MADRL	TBD	TBD
FeUdal Networks	Vezhnevets, A.S. et al.	ICML 2017	TBD	HRL	TBD	TBD
Twin Delayed DDPG (TD3)	Fujimoto, S. et al.	ICML 2018	TBD	AC	TBD	TBD
Soft Actor-Critic (SAC)	Haarnoja, T. et al.	ICML 2019	TBD	AC	TBD	TBD
-----------	-----------	-----------	TBD	TBD	TBD	TBD