Share your thoughts, 1 month free Claude Pro on usSee more

Walker2D

Benchmarks

Task Name	Dataset Name	SOTA Result
Offline Reinforcement Learning	walker2d medium	Normalized Score1,248	51
Offline Reinforcement Learning	walker2d medium-replay	Normalized Score99.6	50
Reinforcement Learning	Walker2D v5	Average Return6,335.5	45
Offline Reinforcement Learning	Walker2d D4RL v2 (offline)	Return86.7	32
Offline Reinforcement Learning	Walker2d medium-expert	Normalized Score114.4	31
Offline Reinforcement Learning	Walker2D Medium BodyMass Shift	Average Return94.578	27
Offline Reinforcement Learning	1T10S Walker2D (Medium-Expert)	Score113.069	26
Offline Reinforcement Learning	1T10S Walker2D (Medium-Replay)	Performance Score71.67	26
Offline Reinforcement Learning	1T10S Walker2D (Medium)	Score80.693	26
Reinforcement Learning	Walker2d v3	Average Final Return6,701	26
Offline Reinforcement Learning	walker2d Mixed Dataset	Normalized Reward64.4	24
Offline Reinforcement Learning	Walker2d	Clean Score3,718	21
Per time-step regression	Walker2D	Squared Error0.617	19
Offline Reinforcement Learning	Walker2D Medium-Replay BodyMass Shift	Average Return87.491	18
Offline Reinforcement Learning	Walker2D Medium-Expert 1T10S	Average Return118.564	18
Offline Reinforcement Learning	Walker2D Medium-Replay 1T10S	Average Return87.491	18
Offline Reinforcement Learning	Walker2D Medium 1T10S	Average Return84.582	18
Offline Reinforcement Learning	walker2d medium v2	Normalized Score92.7	18
Reinforcement Learning	Walker2d v4	Avg Return39,641,353	17
Continuous Control	Walker2d v5	Avg Return6,138.2	17
Offline Reinforcement Learning	Walker2d kinematic shifts	Score106	16
Offline Reinforcement Learning	Walker2d	Average Return2,278.9	16
Offline Policy Adaptation	walker2d medium-expert	Normalized Score62.1	14
Offline Policy Adaptation	walker2d medium-replay	Normalized Score63.1	14
Offline Policy Adaptation	walker2d medium	Normalized Score56.7	14

Showing 25 of 116 rows