ResearchBenchmarksOffline Reinforcement Learning on walker2d medium-replay v2Follow375ReturnLRT+Q312.6328.8345361.2Oct 28, 2025Evaluation ResultsMethodMethodLinksReturnOODLRT+QMode=lrt+qMode=lrt+q2025.103753.86QMode=qMode=q2025.103733.76LRTMode=lrtMode=lrt2025.103150.41