Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mahjong on Mahjong 100 held-out trajectories (test)
Loading...
77.2
D_policy
PPO
25.928
39.239
52.55
65.861
Jun 20, 2025
D_policy
Updated 18d ago
Evaluation Results
Method
Method
Links
D_policy
PPO
Demonstrator=Bot C
2025.06
77.2
PPO
Demonstrator=Bot B
2025.06
69.1
PPO
Demonstrator=Bot A
2025.06
67.8
MPPO
Demonstrator=Bot B
2025.06
31.8
MPPO
Demonstrator=Bot A
2025.06
29.7
MPPO
Demonstrator=Bot C
2025.06
27.9
Feedback
Search any
task
Search any
task
