Riad Akrour

trajectory optimization (2) policy update (2) interactive learning (1) policy gradient (1) function approximation (1) preference learning (1) constrained optimization (1) gradient descent (1) exploration exploitation (1) policy iteration (1) approximate policy iteration (1) bayesian optimization (1) utility function (1) model-free reinforcement learning (1) reward shaping (1) preference-based reinforcement learning (1) action space (1) model-free learning (1) motor skill (1) model-free algorithm (1)