Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
POMDP Simulation on RS(8, 4, 10, -1)
Loading...
16.9
Reward
Naive
9.828
11.664
13.5
15.336
Sep 27, 2022
Reward
Suggestion Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
Suggestion Count
Naive
v=1
2022.09
16.9
8.4
Perfect
2022.09
16.7
-
Scaled Agent
tau=0.99
2022.09
16.4
2.8
Noisy Agent
lambda=5
2022.09
16.4
4.6
Scaled Agent
tau=0.5
2022.09
16.3
3.2
Noisy Agent
lambda=2
2022.09
16.3
4.5
Scaled Agent
tau=0.75
2022.09
16.2
2.8
Noisy Agent
lambda=1
2022.09
16.2
5.2
Naive
v=0.75
2022.09
14.6
7.7
Naive
v=0.5
2022.09
12.7
7.8
Normal
2022.09
10.1
-
Feedback
Search any
task
Search any
task