3 papers
cs.LG2026
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
Junseok Kim, Dohyeong Kim, Mineui Hong +1
Compositional generalization is essential for reaching unseen goals under novel contextual variations in offline goal-conditioned reinforcement learning (GCRL), where a generalist…
cs.AI2024
Semantic Environment Atlas for Object-Goal Navigation
Nuri Kim, Jeongho Park, Mineui Hong +1
In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes s…
cs.LG2024
Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning
Dohyeong Kim, Mineui Hong, Jeongho Park +1
In many real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propos…