Zifeng Zhuang

offline reinforcement learning (2) cross-domain learning (2) test-time adaptation (1) out-of-distribution generalization (1) offline learning (1) transition dynamics (1) data efficiency (1) policy extraction (1) model-based optimization (1) cross-domain adaptation (1) contextual learning (1) support-constrained objective (1) conservative regularization (1) one-shot learning (1) hindsight information matching (1) imitation learning (1)