Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
POMDP Simulation on Tag
Loading...
1.7
Reward
Perfect
-11.196
-7.848
-4.5
-1.152
Sep 27, 2022
Reward
Suggestion Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
Suggestion Count
Perfect
2022.09
1.7
-
Naive
v=1
2022.09
-1.6
3.7
Scaled Agent
tau=0.99
2022.09
-1.8
3.1
Noisy Agent
lambda=5
2022.09
-1.8
3.2
Noisy Agent
lambda=2
2022.09
-2
3.3
Scaled Agent
tau=0.75
2022.09
-2.4
3.3
Noisy Agent
lambda=1
2022.09
-2.4
3.6
Scaled Agent
tau=0.5
2022.09
-3.6
3.9
Naive
v=0.75
2022.09
-3.8
6.1
Naive
v=0.5
2022.09
-6.8
15.2
Normal
2022.09
-10.7
-
Feedback
Search any
task
Search any
task