2 papers
cs.LG2026
Action-Sufficient Goal Representations
Jinu Hyeon, Woobin Park, Hongjoon Ahn +1
In offline goal-conditioned reinforcement learning (GCRL), hierarchical approaches decompose long-horizon tasks into high-level subgoal prediction and low-level action execution. A…
cs.LG2025
Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning
Hongjoon Ahn, Jinu Hyeon, Youngmin Oh +2
We argue that the negative transfer problem occurring when the new task to learn arrives is an important problem that needs not be overlooked when developing effective Continual Re…