Sridhar Mahadevan

reinforcement learning (3) markov decision process (3) basis function (2) value function (2) policy learning (1) markov decision processes (1) graph laplacian (1) feature selection (1) image generation (1) sparse representation (1) policy gradient (1) deep learning (1) constrained optimization (1) dynamic regret (1) hierarchical reinforcement learning (1) convex optimization (1) natural gradient (1) natural actor-critic (1) l1 regularization (1) temporal difference learning (1)