ResearchBenchmarksMeta Reinforcement Learning on 2-D point robot navigation (meta-test)For AI assistantsMarkdownContent indexMeta Reinforcement Learning on 2-D point robot navigation (meta-test)Follow-19.2Average ReturnDR-MAML+-21.176-20.663-20.15-19.637Oct 30, 2024Evaluation resultsMethodMethodLinksAverage ReturnCVaR ReturnDR-MAML+Number of runs=4, alph...Number of runs=4, alpha (α)=0.52024.10-19.2-28.4DR-MAMLNumber of runs=4, alph...Number of runs=4, alpha (α)=0.52024.10-19.6-28.9DRO-MAMLNumber of runs=4, alph...Number of runs=4, alpha (α)=0.52024.10-20.9-29MAMLNumber of runs=4, alph...Number of runs=4, alpha (α)=0.52024.10-21.1-29.2