garage
stable

Getting Started

  • Installation
  • Quick Start with garage

Usage Guide (How-To)

  • Run Experiments
  • Use Image Observations
  • Monitor Your Experiments with TensorBoard
  • Train a Policy to Solve an Environment
  • Save, load and resume experiments
  • Load and Use a Trained Policy
  • Use a pre-trained network to start a new experiment
  • Run garage with Docker
  • Ensure your experiments are reproducible
  • Run Meta-/Multi-Task RL Experiments
  • Maximize resource usage

Tutorials

  • Adding a New Environment
  • Implement a New Algorithm
  • Change how your algorithm samples (Implement a Custom Worker)

Algorithms and Methods

  • Behavioral Cloning
  • ERWR
  • TRPO
  • Multi-Task TRPO
  • Soft Actor-Critic
  • Multi-Task Soft Actor-Critic
  • Probablistic Embeddings for Actor-Critic Reinforcement Learning (PEARL)
  • RL2
  • Proximal Policy Optimization
  • MAML
  • Multi-Task Proximal Policy Optimization (Multi-Task PPO)
  • REINFORCE
  • Twin Delayed Deep Deterministic (TD3)
  • DDPG

Reference Guide

  • Environment
  • Environment Libraries
  • Experiment
  • Sampling

Development Guide

  • Setting up your development environment
  • Testing
  • Benchmarking
  • Writing Documentation
  • Git Workflow
  • Preparing a Pull Request

API Reference

  • garage
  • garage.envs
  • garage.experiment
  • garage.np
  • garage.plotter
  • garage.replay_buffer
  • garage.sampler
  • garage.tf
  • garage.torch
garage
  • Docs »
  • Search
  • Edit on GitHub

© Copyright 2020, garage contributors Revision fea45116.

Built with Sphinx using a theme provided by Read the Docs.

Made with ❤ at and