Daniel J Mankowitz

deep q-network (2) deep reinforcement learning (2) policy learning (2) reinforcement learning (2) bayesian regularization (1) preference learning (1) constraint satisfaction (1) value function approximation (1) sequential decision (1) batch reinforcement learning (1) policy selection (1) lagrangian relaxation (1) directed graph (1) bayesian optimization (1) temporal abstraction (1) lifelong learning (1) skill learning (1) positional encoding (1) least square (1) continuous action (1)