Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Identifiable Token Correspondence for World Models
Youngin Kim, Ray Sun, Inho Kim +2
Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, includin…
cs.LG2023
Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning
Seungyong Moon, Junyoung Yeom, Bumsoo Park +1
Discovering achievements with a hierarchical structure in procedurally generated environments presents a significant challenge. This requires an agent to possess a broad range of a…