Offline Reinforcement Learning

Benchmarks

Dataset Name	SOTA Method	Metric
D4RL halfcheetah-medium-expert	VIPO	Normalized Score110	117	4d ago
D4RL hopper-medium-expert	ATAC	Normalized Score119.2	115	4d ago
D4RL walker2d-medium-expert	ATAC	Normalized Score114.2	86	4d ago
D4RL walker2d-random	AWAC	Normalized Score510	77	4d ago
D4RL Medium-Replay Hopper	NEUBAY	Normalized Score110.6	72	4d ago
D4RL halfcheetah-random	ADMPO	Normalized Score45.4	70	4d ago
D4RL Walker2d Medium v2	PMDB	Normalized Return94.2	67	4d ago
D4RL hopper-random	MOREL	Normalized Score53.6	62	4d ago
Kitchen Partial	GCPC	Normalized Score90.2	62	4d ago
D4RL Medium-Replay HalfCheetah	RAMBO	Normalized Score77.6	59	4d ago
D4RL Medium HalfCheetah	SUMO	Normalized Score84.3	59	4d ago
D4RL Medium Walker2d	NEUBAY	Normalized Score106.4	58	4d ago
D4RL halfcheetah v2 (medium-replay)	CQL	Normalized Score76.9	58	4d ago
D4RL halfcheetah-expert v2	EDAC	Normalized Score106.8	56	4d ago
D4RL walker2d-expert v2	PMDB	Normalized Score115.9	56	4d ago
D4RL hopper-expert v2	CEIL	Normalized Score113	56	4d ago
OGBench antmaze-large-navigate-singletask task1-v0 to task5-v0	GFP	Score95.6	55	4d ago
D4RL Hopper-medium-replay v2	EDAC	Normalized Return107.4	54	4d ago
D4RL Gym walker2d (medium-replay)	ROMI-CQL	Normalized Return109.7	52	4d ago
hopper medium	QDFM	Normalized Score3,729	52	4d ago
walker2d medium	QDFM	Normalized Score1,248	51	4d ago
walker2d medium-replay	Proposed	Normalized Score99.6	50	4d ago
D4RL Hopper-medium-expert v2	PMDB	Normalized Return111.8	49	4d ago
D4RL walker2d-medium-replay	NEUBAY	Normalized Score99.3	45	4d ago
D4RL walker2d-medium-expert v2	EDAC-10	Normalized Score115.4	44	4d ago

Showing 25 of 578 rows

...