kaifronsdal/Crux

Crux.jl

Deep RL library with concise implementations of popular algorithms. Implemented using Flux.jl and fits into the POMDPs.jl interface.

Supports CPU and GPU computation and implements the following algorithms:

Reinforcement Learning

• Deep Q-Learning
  • Prioritized Experience Replay
• REINFORCE
• Proximal Policy Optimization (PPO)
• Advantage Actor Critic
• Deep Deterministic Policy Gradient (DDPG)
• Twin Delayed DDPG (TD3)
• Soft Actor Critic (SAC)

Imitation Learning

• Behavioral Cloning
• Generative Adversarial Imitation Learning (GAIL)
• Adversarial value moment imitation learning (AdVIL)
• (AdRIL)
• (SQIL)
• valueDICE
• Adversarial Soft Advantage Fitting (ASAF)

Note for imitation learning algorithms: The parameter normalize_demo::Bool determines if the provided expert demonstrations should be normalized by the state and action spaces provided to the solver.

Installation

• Install POMDPGym
• Install by opening julia and running ]add git@github.com:ancorso/Crux.git

To edit or contribute use ]dev Crux and the repo will be cloned to ~/.julia/dev/Crux

Maintained by Anthony Corso (acorso@stanford.edu)