Malayandi Palan

inverse reinforcement learning (2) preference learning (2) reward learning (2) active learning (2) human-robot interaction (1) robot learning (1) reward function (1) demonstration learning (1) information gain (1) preference-based learning (1) human demonstration (1) linear control policy (1) policy fitting (1) kalman constraint (1) lqr problem (1) admm optimization (1) question generation (1) active reward learning (1)