Minghui Zhu

constrained optimization (3) inverse reinforcement learning (3) online learning (2) bilevel optimization (2) distributed learning (2) bi-level optimization (2) gaussian process (1) optimal control (1) value function (1) reward function (1) reward function estimation (1) generalization bound (1) streaming datum (1) gradient approximation (1) meta-reinforcement learning (1) policy adaptation (1) task distribution (1) trajectory learning (1) distributed online learning (1) byzantine tolerance (1)