Dong-Ki Kim

multiagent reinforcement learning (2) graph neural network (2) large language model (2) multi-agent reinforcement learning (2) agent navigation (1) sequential decision making (1) policy optimization (1) in-context learning (1) sequential decision-making (1) response generation (1) knowledge transfer (1) task-oriented dialogue (1) intent classification (1) graph representation (1) hierarchical reinforcement learning (1) graph structure (1) message passing (1) temporal abstraction (1) partially observable environment (1) self-supervised learning (1)