Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Policy Evaluation on 400-State Random MDP off-policy (Sum of sqrt MSE)
Loading...
29.65
Sum of sqrt MSE
BBO
13.1176
124.7113
236.305
347.8987
Jun 9, 2021
Sum of sqrt MSE
Updated 1mo ago
Evaluation Results
Method
Method
Links
Sum of sqrt MSE
BBO
Policy Type=off-policy
2021.06
29.65
LSTD+
Policy Type=off-policy
2021.06
29.65
BRM
Policy Type=off-policy
2021.06
32.13
TD
Policy Type=off-policy
2021.06
113.3
TDC
Policy Type=off-policy
2021.06
266.36
GTD2
Policy Type=off-policy
2021.06
442.96
Feedback
Search any
task
Search any
task