arXiv (Cornell University) · 2019 · 29 citations · 10 references
ComputingComputer ScienceArtificial IntelligenceDistributed SystemsMachine LearningDistributed ComputingReinforcement LearningScalable Algorithm DesignScalable Machine LearningDistributed Machine LearningParallel InferenceParallel Machine Learning
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 \url{https://github.com/facebookresearch/torchbeast}.
10
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
David Silver, Thomas Hubert, Julian Schrittwieser et al. · Science · 2018 · 3.5K citations · Full text
End-to-end training of deep visuomotor policies
Sergey Levine, Chelsea Finn, Trevor Darrell et al. · Journal of Machine Learning Research · 2016 · 1.7K citations