List your company

Offline Reinforcement Learning on D4RL Hopper v2 (test)

776.7Mean Episode RewardRGMDT
173.344329.9845486.625643.2655Oct 21, 2024

Evaluation results

MethodLinks
RGMDTSample Size=80,000 samples, Node Count=64 nodes2024.10776.7
RGMDTSample Size=80,000 samples, Node Count=40 nodes2024.10567.27
RFSample Size=800,000 samples, Node Count=64 nodes2024.10489.92
RGMDTSample Size=800,000 samples, Node Count=40 nodes2024.10467.27
CARTSample Size=800,000 samples, Node Count=64 nodes2024.10460.9
RGMDTSample Size=800,000 samples, Node Count=64 nodes2024.10458.7
CARTSample Size=800,000 samples, Node Count=40 nodes2024.10458.47
RFSample Size=800,000 samples, Node Count=40 nodes2024.10456.41
RFSample Size=80,000 samples, Node Count=64 nodes2024.10452.89
ETSample Size=800,000 samples, Node Count=64 nodes2024.10451.8
ETSample Size=80,000 samples, Node Count=64 nodes2024.10448.98
CARTSample Size=80,000 samples, Node Count=64 nodes2024.10448.85
CARTSample Size=80,000 samples, Node Count=40 nodes2024.10443.47
ETSample Size=800,000 samples, Node Count=40 nodes2024.10441.01
RFSample Size=80,000 samples, Node Count=40 nodes2024.10345.81
ETSample Size=80,000 samples, Node Count=40 nodes2024.10196.55