Sebastian Flennerhag

neural network (2) neural network optimization (1) gradient descent (1) constrained markov decision process (1) last-iterate convergence (1) optimistic method (1) meta reinforcement learning (1) activation function (1) gradient descent-ascent (1) constrained mdp (1) feed-forward layer (1) constrained rl (1) adaptive parameterization (1) black-box learning (1) black-box approach (1) policy optimization (1) word modeling (1)