Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Counterfactual Policy Evaluation on GridWorld p = 0.9
Loading...
346
Avg Worst-Case Counterfactual V(s0)
ICFMDP
302.32
313.66
325
336.34
Feb 19, 2025
Avg Worst-Case Counterfactual V(s0)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg Worst-Case Counterfactual V(s0)
ICFMDP
Sampled observed traje...
2025.02
346
Gumbel-max
Sampled observed traje...
2025.02
304
Feedback
Search any
task
Search any
task