Ted Moskovitz

reinforcement learning (2) policy evaluation (1) neural network training (1) policy optimization (1) policy gradient (1) in-context learning (1) multitask learning (1) neural network optimization (1) natural gradient (1) continuous control (1) state representation (1) off-policy learning (1) l2 regularization (1) constrained markov decision process (1) synthetic datum (1) last-iterate convergence (1) optimistic method (1) in-weights learning (1) successor representation (1) gradient descent-ascent (1)