Richard Lewis

reinforcement learning (2) visual reasoning (2) self-supervised learning (1) language model evaluation (1) recurrent neural network (1) working memory (1) perceptual decision making (1) intrinsic reward (1) agent learning (1) entropy reduction (1) relational reasoning (1) language model (1) adaptive agent (1) sparse reward (1) in-context learning (1) pre-trained language model (1) reward function learning (1) transformer language model (1) reinforcement learning agent (1) zero-shot learning (1)