Meta-World+: An Improved, Standardized, RL Benchmark

Reginald McLean, Evangelos Chatzaroulas, Luc McCutcheon, Frank Röder, Tianhe Yu, Zhanpeng He, K.R. Zentner, Ryan Julian, J K Terry, Isaac Woungang, Nariman Farsad, Pablo Samuel Castro

Toronto Metropolitan University· Farama Foundation· University of Surrey· Hamburg University of Technology· Columbia University· Google· University of Southern California· Université de Montréal· Mila

multi-task reinforcement learning meta-reinforcement learning

⋅ NeurIPS ⋅ Project Page ⋅Poster ⋅OpenReview

Abstract

Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design.

Through this process we release an open-source version of Meta-World that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.