Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Single-agent Reinforcement Learning (SARL) on Breakout Poisoned

570.9Average Episode Return

SHINE

1.292149.171297.05444.929May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
570.9
517.8
2026.05
444.6
2026.05
404
309
2026.05
220.7
2026.05
33.1
2026.05
31
2026.05
23.2