Table of Contents


RL社区

专栏

Code

Documents

Books

Course

Recent Papers

  • 2019 - Modern Deep Reinforcement Learning Algorithms [Paper]
  • 2019 - Nvidia - GPU-Accelerated Atari Emulation for Reinforcement Learning [Paper] [Github]

Blog

RL Paper Slide and Code

  • (TD3) Addressing Function Approximation Error in Actor-Critic Methods
    • Scott Fujimoto, Herke van Hoof, David Meger
    • McGill University, University of Amsterdam (阿姆斯特丹大学)
    • ICML’18
    • [Paper] [Github-Pytorch] [Talk]
    • Other Paper
      • ICML’19: Off-Policy Deep Reinforcement Learning without Exploration

Conference

DRL Workshop

Exploration

Ian Osband (DeepMind)

  • Homepage
  • Phd Thesis (2016): Deep Exploration via Randomized Value Functions
    • [Thesis][Video][Slide]
    • Statistically efficient RL requires “deep exploration”. Previous approaches to deep exploration have not been computationally tractable beyond small scale problems. This dissertation presents an alternative approach through the use of randomized value functions.
  • ICML2016: Generalization and Exploration via Randomized Value Functions

深度文章