Baconian
master

Installation

  • Installation Guide

Tutorial and Examples

  • Step by step guide to run a RL experiment
  • Best practice and core concepts of Baconian
  • Examples
    • DQN with Acrobot-v1
    • DDPG with Pendulum-v0
    • PPO with Pendulum-v0
    • MPC with Pendulum-v0
    • Dyna with Pendulum-v0
    • Gaussian Process Dynamics
    • Early Stopping Flow (DDPG with Pendulum-v0)
    • Environment Wrapper (MountainCarContinuous-v0, RewardWrapper)
    • Use scheduler module in experiments
    • Visualization of experiments log
  • Logging and Visualization
  • How to implement a new algorithm
  • How to implement a new environment
  • How to implement a new dynamics model

Design of Baconian

  • System Overview of Baconian

Baconian API Reference

  • Baconian API Reference

Contribute

  • Contributions
Baconian
  • Docs »
  • Examples
  • Edit on GitHub

ExamplesΒΆ

We offer some examples on how to better use Baconian in a more practical and efficient way.

Model-Free algorithm examples

  • DQN with Acrobot-v1
  • DDPG with Pendulum-v0
  • PPO with Pendulum-v0

Model-Based algorithm examples

  • MPC with Pendulum-v0
  • Dyna with Pendulum-v0
  • Gaussian Process Dynamics

Utility examples

  • Early Stopping Flow (DDPG with Pendulum-v0)
  • Environment Wrapper (MountainCarContinuous-v0, RewardWrapper)
  • Use scheduler module in experiments
  • Visualization of experiments log
Next Previous

© Copyright 2019, Linsen Dong Revision e84508da.

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