Jeonghye Kim

policy learning (2) reinforcement learning (2) offline reinforcement learning (1) decision making (1) supervised learning (1) neural architecture (1) value function (1) value iteration (1) exploration strategy (1) deep rl (1) conditional supervised learning (1) exploration-exploitation trade-off (1) agent system (1) option framework (1) reflection mechanism (1) large language model (1) option-critic architecture (1) return-conditioned supervised learning (1) goal alignment (1) goal reasoning (1)