Yecheng Jason Ma

model-based reinforcement learning (2) sample efficiency (1) imitation learning (1) sim-to-real transfer (1) uncertainty quantification (1) trajectory forecasting (1) likelihood sampling (1) diverse sampling (1) domain randomization (1) constraint satisfaction (1) reward function (1) policy improvement (1) generalization ability (1) reward learning (1) robot manipulation (1) safe reinforcement learning (1) normalizing flow (1) policy training (1) vision-language model (1) robotic control (1)