TL
TL;DR
The components of OpenAI Gym and the design decisions that went into the software are discussed, which includes a growing collection of benchmark problems that expose a common interface.
Abstract
OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.
References18 items
1
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
2
Benchmarking Deep Reinforcement Learning for Continuous Control
3
Asynchronous Methods for Deep Reinforcement Learning
4
RLPy: a value-function-based reinforcement learning framework for education and research
5