Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Imperfect World Models are Exploitable
Logan Mondal Bhamidipaty, Esmeralda S. Whitammer, David Abel +2
We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred o…
cs.AI2025
Repairing Reward Functions with Feedback to Mitigate Reward Hacking
Stephane Hatgis-Kessell, Logan Mondal Bhamidipaty, Emma Brunskill
Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optim…