/Ssup

Primary LanguagePythonMIT LicenseMIT

Self-Supervised RL (SSup) (temporary name)

Forked from stable-baselines.

Documentation

Documentation is available online: https://stable-baselines.readthedocs.io/

Work-in-progress:

stable-baselines/ppo2_ssup/ppo2/PPO2_SSup

TODO:

  • Setup dev environment on flanders
  • Specify pseudo-code
  • Set initial hyper-parameters values
  • Implementation for PPO
  • xp + tune hyper-parameters
  • Validation with additional xps (similar states vs. timesteps, etc.)