Efficient Reinforcement Learning Experimentation in PyTorchDownload PDF


Sep 29, 2021 (edited Oct 04, 2021)ICLR 2022 Conference Blind SubmissionReaders: Everyone
  • Keywords: Deep Reinforcement Learning, Python library
  • Abstract: Abstract: Deep reinforcement learning (RL) has proved successful at solving challenging environments but often requires long training times and very many samples. Furthermore, advancing artificial intelligence requires to easily prototype new methods, yet avoiding impractically slow experimental turnaround times. To this end, we present a PyTorch-based library for RL with a modular design that allows composing agents based on three components types: actors, storages and algorithms. Additionally, the definition of synchronous and asynchronous architectures is permitted with flexibility and independence of the components. We present several standard use-cases of the library and showcase its potential by obtaining the highest to-date test performance on the Obstacle Tower Unity3D challenge environment. In summary, we believe that this work helps accelerate experimentation of new ideas, simplifying research and enabling to tackle more challenging RL problems.
  • One-sentence Summary: PyTorch-based library for RL that allows decomposing agents into independent reusable components for faster method research and exploring accelerated training with multiple distributed training schemes.
  • Supplementary Material: zip
0 Replies