Arunkumar Byravan

offline reinforcement learning (2) policy optimization (1) sim-to-real transfer (1) transfer learning (1) robot learning (1) reproducing kernel hilbert space (1) trajectory optimization (1) model-based reinforcement learning (1) robot manipulation (1) collision avoidance (1) fluid dynamics (1) model-free reinforcement learning (1) vision-based policy (1) bipedal locomotion (1) kernel methods (1) proprioceptive sensing (1) latent dynamics model (1) simulation-to-reality transfer (1) value gradient (1) functional gradient descent (1)