Yi-Chen Li

multi-agent reinforcement learning (1) continual learning (1) catastrophic forgetting (1) few-shot learning (1) offline reinforcement learning (1) preference learning (1) in-context learning (1) batch active learning (1) memory retrieval (1) reward model (1) behavior policy (1) value overestimation (1) trajectory representation (1) policy regularization (1) multi-objective reinforcement learning (1) query strategy (1) deep q-network (1) dataset constraint (1) active learning strategy (1)