Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Game Playing on Leduc Poker
Loading...
3.5
Raw Reward
QL
-0.1296
0.8127
1.755
2.6973
May 4, 2026
Raw Reward
Normalized Performance
Updated 15d ago
Evaluation Results
Method
Method
Links
Raw Reward
Normalized Performance
QL
Masking condition=Adve...
2026.05
3.5
36.7
PPO
Masking condition=Adve...
2026.05
3.32
36.9
NFSP
Masking condition=Adve...
2026.05
1.58
44
PPO
Masking condition=None
2026.05
0.08
49.7
QL
Masking condition=None
2026.05
0.05
50.2
NFSP
Masking condition=None
2026.05
0.01
50
Feedback
Search any
task
Search any
task