Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning

Linsen Dong, Guanyu Gao, Xinyi Zhang, Liangyu Chen, Yonggang Wen
4/23/2019
cs.LGcs.AIstat.ML

Official code: cap-ntu/baconian-project (114 stars, MIT, last commit 2020-05-22).

Abstract

Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics. It has been widely adopted in the research of robotics, autonomous driving, etc. Despite its popularity, there still lacks some sophisticated and reusable open-source frameworks to facilitate MBRL research and experiments. To fill this gap, we develop a flexible and modularized framework, Baconian, which allows researchers to easily implement a MBRL testbed by customizing or building upon our provided modules and algorithms. Our framework can free users from re-implementing popular MBRL algorithms from scratch thus greatly save users' efforts on MBRL experiments.

View on arXivView PDF

Code Implementations(1)

cap-ntu/baconian-projectOfficial100%
MIT

Model-based Reinforcement Learning Framework

1148Shell, PythonMar 31, 20196 years agoMIT
model-basedmodel-based-reinforcement-learningmodel-based-rlreinforcement-learningreinforcement-learning-algorithms

Similar Papers

Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance

82% match1 repo12026

Manipulate-Anything: Automating Real-World Robots using Vision-Language Models

81% match2024

The Control Toolbox - An Open-Source C++ Library for Robotics, Optimal and Model Predictive Control

81% match2018

A Design Co-Pilot for Task-Tailored Manipulators

80% match2025

Smooth Exploration for Robotic Reinforcement Learning

80% match1 repo13.9k2020

Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

79% match1 repo32026

Cite this paper

@article{dong2019baconian,
  title  = {Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning},
  author = {Linsen Dong and Guanyu Gao and Xinyi Zhang and Liangyu Chen and Yonggang Wen},
  year   = {2019},
  eprint = {1904.10762},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.10762}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.10762.svg)](https://codeofpaper.com/paper/1904.10762)

Discussion