conftrace_

worst-case reward

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial perturbation (2) markov decision process (2) robust reinforcement learning (2) policy optimization (2) reinforcement learning (2) set-max policy (1) set improving policy (1) proxy reward (1) generalized policy improvement (1) policy composition (1)

Papers

Goodhart's Law in Reinforcement Learning ICLR 2024 Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning NeurIPS 2022 Discovering a set of policies for the worst case reward ICLR 2021 Robust Deep Reinforcement Learning through Adversarial Loss NeurIPS 2021 Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes NeurIPS 2018