Edoardo Cetin

deep reinforcement learning (3) temporal-difference learning (2) off-policy reinforcement learning (2) reinforcement learning (2) transfer learning (1) decision making (1) policy gradient (1) policy learning (1) computational efficiency (1) markov chain (1) off-policy learning (1) adaptive regularization (1) end-to-end learning (1) action space (1) steady-state distribution (1) memory-based learning (1) convolutional encoder (1) overestimation bia (1) routine learning (1) catastrophic self-overfitting (1)