Skip to yearly menu bar Skip to main content


Contributed Talk
in
Workshop: CODEML: Championing Open-source DEvelopment in Machine Learning

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

Reginald McLean

[ ] [ Project Page ]
Fri 18 Jul 11:30 a.m. PDT — 11:45 a.m. PDT

Abstract:

Multi-task reinforcement learning challenges agents to master diverse skills simultaneously, and Meta-World emerged as the gold standard benchmark for evaluating these algorithms. However, since the introduction of the Meta-World benchmark there have been numerous undocumented changes which inhibit fair comparison of multi-task and meta reinforcement learning algorithms. This work strives to disambiguate these results from the literature, while also producing an open-source version of Meta-World that has full reproducibility of past results.

Chat is not available.