/myrl

Implementations of some standard reinforcement learning algorithms

Primary LanguagePythonMIT LicenseMIT

myrl

Implementations of some standard reinforcement learning algorithms

  • Written in pytorch
  • All implentations are encapsulated into a single file
  • Algorithms implemted as classes which take OpenAI gym env as inputs
  • All classes have uniform interface with train and eval methods
  • All references are given in the code

Algorithms -

  • Vanilla Policy Gradient (VPG)
  • Deep Q Network (DQN)
  • Deep Deterministic Policy Gradient (DDPG)
  • Twin Delayed DDPG (TD3)
  • Soft Actor Critic
  • Proximal Policy Optimization
  • Trust Region Policy Optimization

Features to add -

  • Better hyperparamter management
  • Adding tensorboard logging
  • Add documentation for each algorithm
  • Add results for each algorithm