Skip to content
conftrace_

pessimistic policy

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

risk-aware reinforcement learning (1) worst-case expected reward (1) novel failure mode (1) belief state inference (1) state purification (1) safe exploration (1) world model (1) confidence set (1) reward model (1) adversarial perturbation (1)

Papers

Corruption Robust Offline Reinforcement Learning with Human Feedback AISTATS 2025 Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning AAAI 2025 Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations ICLR 2024 Pessimism About Unknown Unknowns Inspires Conservatism COLT 2020