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

Multi-agent Offline Reinforcement Learning on MPE World Expert

135.2Score

DoF

69.36886.459103.55120.641Sep 22, 2023Feb 22, 2024Jul 24, 2024Dec 25, 2024May 27, 2025Oct 27, 2025Mar 30, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.03
135.2
2026.03
133
2023.09
119.7
2026.03
119.7
2026.03
112.3
2023.09
110.4
2026.03
110.4
2023.09
110.3
2026.03
110.3
2023.09
109.5
2023.09
107.8
2026.03
107.8
2023.09
107.6
2023.09
99.7
2026.03
99.7
2023.09
71.9