conftrace_

policy deception

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

reward ambiguity (1) multi-agent system (1) deceptive behavior (1) boltzmann rationality (1) deceptive inflation (1) human feedback (1) partial observability (1) belief state (1) reinforcement learning from human feedback (1) policy optimization (1)

Papers

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback NeurIPS 2024