Yunqiu Xu

text-based game (5) reinforcement learning (3) knowledge graph (2) language model (2) deep reinforcement learning (2) weakly supervised learning (1) question answering (1) commonsense knowledge (1) video restoration (1) visual grounding (1) hierarchical alignment (1) hierarchical reinforcement learning (1) world model (1) multimodal large language model (1) exploration strategy (1) goal-conditioned reinforcement learning (1) action space (1) retinex theory (1) pretrained language model (1) self-imitation learning (1)