2 papers
cs.AI2026
HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RL
JunHyeok Oh, Zian Jang, Byung-Jun Lee
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically spe…
cs.AI2024
Unsupervised Training of Diffusion Models for Feasible Solution Generation in Neural Combinatorial Optimization
Seong-Hyun Hong, Hyun-Sung Kim, Zian Jang +3
Recent advancements in neural combinatorial optimization (NCO) methods have shown promising results in generating near-optimal solutions without the need for expert-crafted heurist…