Behaviour Suite for Reinforcement Learning

📖 Description

Published as a conference paper at ICLR 2020 Behaviour Suite for Reinforcement Learning Ian Osband?, Yotam Doron, Matteo Hessel, John Aslanides Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvari Satinder Singh, Benjamin Van Roy, Richard Sutton, David Silver, Hado Van Hasselt DeepMind Abstract This paper introduces the Behaviour Suite for Reinforcement Learning , or bsuite for short. bsuite is a collection of carefully-designed experiments that investigate core capabilities of reinforcement learning (RL) agents with two objectives. First, to collect clear, informative and scalable problems that capture key issues in the design of general and e?cient learning al- gorithms. Second, to study agent behaviour through their performance on these shared benchmarks. To complement this e?ort, we open source github.com/deepmind/bsuite , which automates evaluation and analysis of any agent on bsuite . This library facilitates reproducible and accessible research on th...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1908.03568