Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research
Captured source
source ↗Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research | OpenAI
February 26, 2018
Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research
Loading…
Share
Abstract
The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent is told what to do using an additional input. The second part of the paper presents a set of concrete research ideas for improving RL algorithms, most of which are related to Multi-Goal RL and Hindsight Experience Replay.
Authors
Matthias Plappert, Marcin Andrychowicz, Alex Ray, Bob McGrew, Bowen Baker, Glenn Powell, Jonas Schneider, Josh Tobin, Maciek Chociej, Peter Welinder, Vikash Kumar, Wojciech Zaremba
Related articles
Scaling laws for reward model overoptimizationPublicationOct 19, 2022
Learning to play Minecraft with Video PreTrainingConclusionJun 23, 2022
Dota 2 with large scale deep reinforcement learningPublicationDec 13, 2019