Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Offline Inverse Reinforcement Learning research benchmarks · SOTA2 Research

Offline Inverse Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

D4RL HalfCheetah Medium v2

9,313.29Cumulative Reward

8

Feb 26, 2026

MuJoCo walker2d medium-exp

Expert Performance

5,383.98Average Reward

5

Feb 26, 2026

MuJoCo halfcheetah (medium-exp)

Expert Performance

12,174.61Average Reward

5

Feb 26, 2026

MuJoCo hopper (medium-exp)

Expert Performance

3,512.09Average Reward

5

Feb 26, 2026

MuJoCo walker2d (medium-replay)

Expert Performance

5,383.98Avg Reward

5

Feb 26, 2026

MuJoCo halfcheetah (medium-replay)

Expert Performance

12,174.61Average Reward

5

Feb 26, 2026

MuJoCo hopper (medium-replay)

Expert Performance

3,512.09Average Reward

5

Feb 26, 2026

MuJoCo walker2d medium

Expert Performance

5,383.98Avg Reward

5

Feb 26, 2026

MuJoCo halfcheetah (medium)

Expert Performance

12,174.61Average Reward

5

Feb 26, 2026

MuJoCo hopper medium

Expert Performance

3,512.09Average Reward

5

Feb 26, 2026

D4RL Walker2d Medium-Expert v2

4,049.43Cumulative Reward

4

Feb 26, 2026

D4RL HalfCheetah v2 (medium-expert)

10,812.15Cumulative Reward

4

Feb 26, 2026

D4RL Hopper Medium-Expert v2

3,366.23Cumulative Reward

4

Feb 26, 2026

D4RL Walker2d Medium-Replay v2

4,100.99Cumulative Reward

4

Feb 26, 2026

D4RL Hopper Medium-Replay v2

2,417.83Cumulative Reward

4

Feb 26, 2026

D4RL Walker2d Medium v2

4,121.68Cumulative Reward

4

Feb 26, 2026

D4RL Hopper Medium v2

2,417.83Cumulative Reward

4

Feb 26, 2026

Popular datasets

D4RL MuJoCo Walker2d MuJoCo Hopper MuJoCo D4RL Walker2d

Follow for updates

Join SOTA2 Contact