Peter R. Wurman

out-of-distribution generalization (2) reinforcement learning (2) domain generalization (1) robotics control (1) policy selection (1) successor feature (1) policy exploration (1) diverse policy (1) multi-context robotics (1) robust control (1) contextual reinforcement learning (1) two-player game (1) policy diversity (1) neural network (1) test case selection (1) robust testing (1) multi-task learning (1)