Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

OpenAI Gym

About

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.

Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, Wojciech Zaremba• 2016

Related benchmarks

TaskDatasetResultRank
Robotic Path PlanningMaze2D (test)
BS1-0.999
22
Reinforcement LearningAutonomous Driving Dataset
Sample Time (s)31.34
19
Dexterous ManipulationD4RL Adroit Relocate (offline)
Safety Score0.00e+0
9
Locomotion Planningwalker2d medium
Safety0.02
7
LocomotionHopper Med-Expert
Safety0.05
7
Locomotion Planninghopper medium
Safety0.05
7
NavigationMaze2D large
Computation Time (sec)0.02
7
LocomotionHopper Med-Expert
Computation Time (sec)0.06
7
Locomotionhopper medium
Computation Time (sec)0.06
7
Locomotionwalker2d medium
Computation Time (sec)0.06
7
Showing 10 of 14 rows

Other info

Follow for update