25 citations · 33 across the 12 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
Mia Taylor, James Chua, Jan Betley +2
Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in…
cs.AI2023★ 1 cited
BridgeHand2Vec Bridge Hand Representation
Anna Sztyber-Betley, Filip Kołodziej, Jan Betley +1
Contract bridge is a game characterized by incomplete information, posing an exciting challenge for artificial intelligence methods. This paper proposes the BridgeHand2Vec approach…