Kaushik Subramanian

out-of-distribution generalization (2) reinforcement learning (2) domain generalization (1) preference learning (1) robotics control (1) bayesian approach (1) interactive reinforcement learning (1) human feedback (1) policy shaping (1) successor feature (1) policy exploration (1) diverse policy (1) multi-context robotics (1) robust control (1) contextual reinforcement learning (1) reward signal (1) policy diversity (1) neural network (1) multi-task learning (1)