List your company

ResearchFormerly WizWand

D4RL Halfcheetah

Benchmarks

TaskDatasetSOTA resultTrendResults

Offline Reinforcement Learning

D4RL HalfCheetah Medium v2

77.9Average Normalized Return

53

D4RL HalfCheetah medium-offline

34.97Normalized Score

36

Offline Reinforcement Learning

D4RL HalfCheetah Medium

54.1Reward

30

Offline Reinforcement Learning

D4RL HalfCheetah Med-Replay v2

52.2Avg Normalized Return

29

Offline Reinforcement Learning

D4RL HalfCheetah Med-Expert v2

105.9Avg Normalized Return

15

D4RL HalfCheetah-medium v2

98.7Online Return (Normalized)

12

Offline Reinforcement Learning

D4RL HalfCheetah-MR

45Normalized Return

11

Offline Reinforcement Learning

D4RL HalfCheetah-M

49Normalized Return

11

Continuous Control

D4RL Halfcheetah medium

49.01Normalized Return

10

Offline Reinforcement Learning

D4RL halfcheetah medium v2 (test)

48.3Normalized Reward

8

Offline Reinforcement Learning

D4RL Halfcheetah Simultaneous (adversarial corruption)

19.72Average Score

8

Offline Inverse Reinforcement Learning

D4RL HalfCheetah Medium v2

9,313.29Cumulative Reward

8

Offline Policy Evaluation

D4RL HalfCheetah medium

100.5RMSE

7

Offline Policy Evaluation

D4RL HalfCheetah medium-replay

46RMSE

7

Inverse Reinforcement Learning

D4RL HalfCheetah medium-expert

12,175Return

6

Offline Reinforcement Learning

D4RL Halfcheetah random v0

4,114Return

6

Continuous Control

D4RL HalfCheetah Medium-Replay

46.86Normalized Score

5

Continuous Control

D4RL HalfCheetah Medium-Expert

96.67Normalized Score

5

Reinforcement Learning

D4RL HalfCheetah no thighs (medium)

3,910Mean Return

4

Reinforcement Learning

D4RL HalfCheetah broken back thigh medium

5,761Mean Return

4

Off-policy Evaluation

D4RL HalfCheetah medium-expert

7.8RMAE

3

Off-policy Evaluation

D4RL HalfCheetah medium

0.247RMAE

3

Reinforcement Learning

D4RL HalfCheetah Med-Expert

75.98D4RL Score

2

Reinforcement Learning

D4RL HalfCheetah Medium

42.16D4RL Score

2