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 Terry · Isaac Woungang · Nariman Farsad · Pablo Samuel Castro
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.
Successful Page Load