Contents Menu Expand Light mode Dark mode Auto light/dark mode
Logo

get started

  • Installation
  • Usage Video

mathematical theory

  • Notations
  • Vector and Martrix
  • Lagrange Duality

base rl algorithm

  • Trust Region Policy Optimization
  • Proximal Policy Optimization Algorithms

safe rl algorithm

  • Constrained Policy Optimization
  • Projection-Based Constrained Policy Optimization
  • First Order Constrained Optimization in Policy Space
  • Lagrangian Methods

base rl api

  • Base On-policy Algorithms

safe rl api

  • First Order Algorithms
  • Second Order Algorithms
  • The Lagrange Algorithms
  • Penalty Function Algorithms

common

  • OmniSafe Buffer
  • OmniSafe Experiment Grid
  • OmniSafe Lagrange Multiplier
  • OmniSafe Normalizer
  • OmniSafe Logger

utils

  • OmniSafe Config
  • OmniSafe Distributed
  • OmniSafe Math
  • OmniSafe Model Utils
  • OmniSafe Tools

models

  • OmniSafe Actor
  • OmniSafe Critic
  • OmniSafe Actor Critic

envs

  • Core
  • Wrapper
  • Safety Gymnasium Environment
  • Adapter
Back to top
Copyright © 2022, OmniSafe Team
Made with Sphinx and @pradyunsg's Furo