Harm Van Seijen

value function (4) reinforcement learning (4) function approximation (2) model-based reinforcement learning (2) temporal-difference learning (2) policy optimization (1) model-based learning (1) discount factor (1) value estimation (1) q-value function (1) planning algorithm (1) eligibility trace (1) model-free learning (1) reward decomposition (1) inverse model (1) prioritized sweeping (1) dead-end state (1) secure exploration (1) bridge effect (1) exogenous information (1)