DeepAI AI Chat
Log In Sign Up

TorchBeast: A PyTorch Platform for Distributed RL

by   Heinrich Küttler, et al.

TorchBeast is a platform for reinforcement learning (RL) research in PyTorch. It implements a version of the popular IMPALA algorithm for fast, asynchronous, parallel training of RL agents. Additionally, TorchBeast has simplicity as an explicit design goal: We provide both a pure-Python implementation ("MonoBeast") as well as a multi-machine high-performance version ("PolyBeast"). In the latter, parts of the implementation are written in C++, but all parts pertaining to machine learning are kept in simple Python using PyTorch, with the environments provided using the OpenAI Gym interface. This enables researchers to conduct scalable RL research using TorchBeast without any programming knowledge beyond Python and PyTorch. In this paper, we describe the TorchBeast design principles and implementation and demonstrate that it performs on-par with IMPALA on Atari. TorchBeast is released as an open-source package under the Apache 2.0 license and is available at <>.


page 1

page 2

page 3

page 4


Pycobra: A Python Toolbox for Ensemble Learning and Visualisation

We introduce pycobra, a Python library devoted to ensemble learning (reg...

EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine

There has been significant progress in developing reinforcement learning...

D2O - a distributed data object for parallel high-performance computing in Python

We introduce D2O, a Python module for cluster-distributed multi-dimensio...

Recommendation in Personalised Peer-Learning Environments

Recommendation in Personalised Peer Learning Environments (RiPPLE) is an...

Synthesis of separation processes with reinforcement learning

This paper shows the implementation of reinforcement learning (RL) in co...

pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Research

Microgrids, self contained electrical grids that are capable of disconne...

Attracting Sets in Perceptual Networks

This document gives a specification for the model used in [1]. It presen...

Code Repositories


A PyTorch Platform for Distributed RL

view repo