Richard S. Sutton

Reinforcement Learning (1)

reinforcement learning (11) value function (7) temporal-difference learning (5) temporal difference learning (5) policy evaluation (5) function approximation (5) off-policy learning (4) markov decision process (3) eligibility trace (3) linear function approximation (3) stochastic gradient descent (3) model-based reinforcement learning (3) convergence analysis (2) bellman error (2) temporal abstraction (2) linear function approximator (1) natural gradient (1) computational neuroscience (1) deep learning (1) online learning (1)