Vivek Veeriah

auxiliary task (3) general value function (3) reinforcement learning (3) representation learning (3) hyperparameter tuning (1) hierarchical reinforcement learning (1) self-supervised learning (1) agent learning (1) anomaly detection (1) temporal abstraction (1) off-policy learning (1) constrained markov decision process (1) long short-term memory (1) information gain (1) last-iterate convergence (1) recurrent neural network (1) optimistic method (1) intrinsic reward (1) state representation (1) policy optimization (1)