Distributed Reinforcement Learning

TorchBeast

Introduced by Küttler et al. in TorchBeast: A PyTorch Platform for Distributed RL

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.

Source: TorchBeast: A PyTorch Platform for Distributed RL

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
OpenAI Gym 1 100.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories