Amrit Bedi

motion planning (1) multi-agent reinforcement learning (1) trajectory prediction (1) model-based reinforcement learning (1) bayesian regret (1) mixing time (1) information gain (1) autonomous vehicle (1) sparse reward (1) integral probability metric (1) multi-level monte carlo (1) intent inference (1) average-reward reinforcement learning (1) stein discrepancy (1) directed exploration (1) heterogeneous traffic (1)