Jongmin Lee

Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments

SpoilDICE: Safe and Performant Offline Imitation Learning from Dual Demonstrations

Agent-Chained Policy Optimization

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Semi-gradient DICE for Offline Constrained Reinforcement Learning

SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation