Sobhan Miryoosefi

constrained reinforcement learning (3) sample complexity (3) language model (2) convex constraint (2) episodic learning (1) policy optimization (1) transfer learning (1) natural language processing (1) reinforcement learning theory (1) model pretraining (1) policy learning (1) neural network optimization (1) bellman equation (1) partially observable markov decision process (1) optimal policy (1) short-term memory (1) concave optimization (1) moment matching (1) safe reinforcement learning (1) inductive bia (1)