Lihe Li

multi-agent reinforcement learning (4) cooperative multi-agent reinforcement learning (2) catastrophic forgetting (1) few-shot learning (1) offline reinforcement learning (1) domain adaptation (1) preference learning (1) in-context learning (1) memory retrieval (1) trajectory distribution (1) adversarial attack (1) variational autoencoder (1) reward model (1) trajectory representation (1) evolutionary algorithm (1) multi-objective reinforcement learning (1) non-stationary environment (1) physics simulation (1) offline domain calibration (1) physics parameter (1)