Reinforcement Learning on Hopper (forward) benchmark leaderboard · SOTA2 Research

Reinforcement Learning on Hopper (forward)

982Average Episodic ReturnCOMBO

Evaluation Results

Method	Links
COMBO2024.03		982
DiSPO2024.03		832
MOPO2024.03		753
USFA2024.03		746
FB2024.03		726
COMBO2024.03		670
RaMP2024.03		652
DiSPO2024.03		566
MOPO2024.03		493
USFA2024.03		487
RaMP2024.03		470
FB2024.03		452