Paper notes

Reinforcement Learning

1. Policy Gradient Methods

2. DQN

3. Multi-agent Learning

4. Guided Policy Search

5. Imitation Learning

6. Transfer Learning

7. NLP

8. Exploration

9. Robot learning

10. Memory

11. Navigation

12. Evolutionary

Environments

• OpenAI Gym

  • Classic control
  • VizDoom
  • Mujoco (select envs)

• OpenAI Universe

  • Flash games
  • World of bits

• Mujoco

• Labyrinth

• Malmo

• Gazebo

  • Gym gazebo

• OpenSim

• Euro Truck Simulator

• Airsim

More resources

Berkeley Deep RL

Robot Learning from Demonstration and Interaction

More papers: https://github.com/andrewliao11/Deep-Reinforcement-Learning-Survey/blob/master/Reinforcement-Learning-Papers.md

CILVR Reading Group

David Silver @ UCL

Nando de Freitas @ UBC

John Schulman @ MLSS

Marcello Restelli Lecture

Pieter Abbeel @ NIPS 2016

Nuts and bolts of RL

Sergey Levine RL Seminar