Conventional reinforcement learning (RL) algorithms exhibit broad generality in their
theoretical formulation and high performance on several challenging domains when …

Efficient exploration in reinforcement learning is a challenging problem commonly
addressed through intrinsic rewards. Recent prominent approaches are based on state …

TD-learning is a foundation reinforcement learning (RL) algorithm for value prediction.
Critical to the accuracy of value predictions is the quality of state representations. In this …

In this paper, we explore an approach to auxiliary task discovery in reinforcement learning
based on ideas from representation learning. Auxiliary tasks tend to improve data efficiency …

Predicting the sensorimotor stream has consistently been a key component for building
general learning agents. Whether through predicting a reward signal to select the best …

Learning control from pixels is difficult for reinforcement learning (RL) agents because
representation learning and policy learning are intertwined. Previous approaches remedy …