Skip to content

Reimplementations of and playground for reinforcement learning algorithms

License

Notifications You must be signed in to change notification settings

juliusrueckin/rl_implementations

Repository files navigation

Reinforcement Learning (RL)

This repository reimplements the most popular reinforcement learning algorithms & components.

Implemented RL Algorithms & Components

  • Deep Q-Learning (parallelized) (DQN)
  • Double Deep Q-Learning (DDQN)
  • Prioritized Experience Replay (PER)
  • Multi-step learning with n-step TD-targets (Sutton and Barto, Chapter 7.1)
  • Dueling network architectures (Dueling DDQN)
  • Noisy networks for exploration (Noisy Nets)
  • Distributional Perspective on Reinforcement Learning (C51)
  • Rainbow: Combining Improvements in Deep Reinforcement Learning (parallelized) (Rainbow)
  • Proximal Policy Optimization Algorithms (parallelized) (PPO)
  • Soft Actor-Critic (parallelized) (SAC)
  • Contrastive Unsupervised Representations for Reinforcement Learning (CURL)
  • Atari tricks: frame stacking, action repetitions, no-ops actions

About

Reimplementations of and playground for reinforcement learning algorithms

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages