conftrace_

lexicographic reward

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multi-objective optimization (2) episode length (1) misspecified setting (1) healthcare policy (1) feature dimension (1) negative side effect (1) policy constraint (1) reward inference (1) lexicographic preference (1) multi-objective reinforcement learning (1)

Papers

Multi-objective Linear Reinforcement Learning with Lexicographic Rewards ICML 2025 Inferring Lexicographically-Ordered Rewards from Preferences AAAI 2022 A Multi-Objective Approach to Mitigate Negative Side Effects IJCAI 2020