yawen-d / key-paper-summary-in-drl

This repository contains the summaries of around 100 key papers on deep reinforcement learning listed in on OpenAI Spinning Up.

Key Paper Summary in DRL

This repository contains the summaries of around 100 key papers on deep reinforcement learning listed in on OpenAI Spinning Up.

01. Model-Free RL

a. Deep Q-Learning

[001] Playing Atari with Deep Reinforcement Learning, Mnih et al, 2013. Algorithm: DQN. [arxiv] [summary]

[002] Deep Recurrent Q-Learning for Partially Observable MDPs, Hausknecht and Stone, 2015. Algorithm: Deep Recurrent Q-Learning. [arxiv] [summary]

[003] Dueling Network Architectures for Deep Reinforcement Learning, Wang et al, 2015. Algorithm: Dueling DQN. [arxiv] [summary]

[004] Deep Reinforcement Learning with Double Q-learning, Hasselt et al 2015. Algorithm: Double DQN. [arxiv] [summary]

[005] Prioritized Experience Replay, Schaul et al, 2015. Algorithm: Prioritized Experience Replay (PER). [arxiv] [summary]

[006] Rainbow-Combining Improvements in Deep Reinforcement Learning, Hessel et al, 2017. Algorithm: Rainbow DQN. [arxiv] [summary]

13. Classic Papers in RL or Review

[100] Policy Gradient Methods for Reinforcement Learning with Function Approximation, Sutton et al, 2000. Contributions: Established policy gradient theorem and showed convergence of policy gradient algorithm for arbitrary policy classes. [paper] [summary]