Our new X account is live! Follow @wizwand_team for updates

hopper

Benchmarks

Task Name	Dataset Name	SOTA Result
Reinforcement Learning	Hopper v5	Average Return3,732.5	93
Offline Reinforcement Learning	hopper medium	Normalized Score3,729	52
Offline Reinforcement Learning	hopper medium-replay	Normalized Score113	44
Offline Reinforcement Learning	Hopper D4RL v2 (offline)	Average Score100.8	32
Offline Reinforcement Learning	Hopper medium-expert	Normalized Score111.6	24
Offline Reinforcement Learning	hopper Mixed Dataset	Normalized Reward108	24
Locomotion	Hopper IID (test)	Mean Episode Reward1,859	24
Locomotion Control	Hopper sigma 0.3 (test)	Episode Reward1,368	24
Locomotion	Hopper	Convergence (%)100	20
Offline Reinforcement Learning	Hopper expert	Normalized Score112.8	19
Continuous Control	Hopper 3-Dof	Final Return2,735	18
Locomotion Control	Hopper sigma 0.7 (test)	Episode Reward443	18
Locomotion Control	Hopper sigma 0.5 (test)	Episode Reward729	18
Locomotion Control	Hopper sigma 0.1 (test)	Episode Reward1,859	18
Offline Reinforcement Learning	Hopper kinematic shifts	Score97	16
Offline Reinforcement Learning	Hopper	Average Return2,116.2	16
Reinforcement Learning	Hopper	Avg Episode Reward2,743.9	15
Continuous Control	hopper	Average Reward2,133,326	15
Offline Reinforcement Learning	Hopper Medium Noise 0	Normalized Return95	14
Offline Reinforcement Learning	Hopper Medium (Noise 5)	Normalized Return70.67	14
Cross-Domain Offline Policy Adaptation	hopper-med Source Target	Normalized Score41.6	14
Offline Policy Adaptation	hopper medium-expert	Normalized Score53.4	14
Offline Policy Adaptation	Hopper medium-replay	Normalized Score36.8	14
Offline Reinforcement Learning	Hopper random	Normalized Score32.2	14
Reinforcement Learning	Hopper v4	Average Return27,721,263	13

Showing 25 of 104 rows