Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Single-agent Reinforcement Learning (SARL) on Seaquest Poisoned
Loading...
1,656.1
Average Episode Return
BehaviorGuard
80.604
489.627
898.65
1,307.673
May 7, 2026
Average Episode Return
Updated 26d ago
Evaluation Results
Method
Method
Links
Average Episode Return
BehaviorGuard
2026.05
1,656.1
BIRD
2026.05
1,630.8
PD
2026.05
825.1
Original
2026.05
141.2
Feedback
Search any
task
Search any
task