Ishan Durugkar

goal-conditioned reinforcement learning (2) multi-agent reinforcement learning (2) policy gradient (2) transfer learning (1) out-of-distribution generalization (1) importance sampling (1) distribution matching (1) value function (1) batch learning (1) value function estimation (1) batch reinforcement learning (1) mean squared error (1) entropy regularization (1) cooperative learning (1) expert demonstration (1) sparse reward (1) reward shaping (1) intrinsic reward (1) dynamics mismatch (1) teammate modeling (1)