Kang Xu

reinforcement learning (2) dynamics mismatch (2) cross-domain adaptation (2) domain adaptation (2) policy transfer (2) diffusion model (1) domain generalization (1) benchmark evaluation (1) argument extraction (1) information extraction (1) event argument extraction (1) domain randomization (1) policy optimization (1) diverse policy (1) in-context learning (1) off-dynamics reinforcement learning (1) behavior regularization (1) natural language processing (1) behavioral cloning (1) offline reinforcement learning (1)