Jiafei Lyu

reinforcement learning (3) model-based reinforcement learning (2) offline reinforcement learning (2) sample efficiency (2) domain randomization (1) domain adaptation (1) image generation (1) reward learning (1) direct preference optimization (1) chain-of-thought reasoning (1) preference learning (1) reinforcement learning from human feedback (1) value function (1) continuous control (1) novelty detection (1) mathematical reasoning (1) distribution shift (1) value estimation (1) benchmark evaluation (1) multi-agent reinforcement learning (1)