Ryan Kortvelesy

Reinforcement Learning (1)

reinforcement learning (3) recurrent neural network (3) memory model (2) partially observable markov decision process (2) partially observable environment (1) recurrent reinforcement learning (1) linear recurrent model (1) aggregation function (1) memory architecture (1) graph neural network (1) graph convolutional memory (1) topological prior (1) representation learning (1) latent markov state (1) sample efficiency (1) function approximation (1) message passing (1)