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 efficient learning algorithms. Second, to study agent behaviour through their performance on these shared benchmarks. To complement this effort, we open source this http URL, which automates evaluation and analysis of any agent on bsuite. This library facilitates reproducible and accessible research on the core issues in RL, and ultimately the design of superior learning algorithms. Our code is Python, and easy to use within existing projects. We include examples with OpenAI Baselines, Dopamine as well as new reference implementations. Going forward, we hope to incorporate more excellent experiments from the research community, and commit to a periodic review of bsuite from a committee of prominent researchers.

Similar Papers

Implementation Matters in Deep RL: A Case Study on PPO and TRPO
Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry,
Measuring the Reliability of Reinforcement Learning Algorithms
Stephanie C.Y. Chan, Samuel Fishman, Anoop Korattikara, John Canny, Sergio Guadarrama,
Sampling-Free Learning of Bayesian Quantized Neural Networks
Jiahao Su, Milan Cvitkovic, Furong Huang,
Making Sense of Reinforcement Learning and Probabilistic Inference
Brendan O'Donoghue, Ian Osband, Catalin Ionescu,