-
CertRL: Formalizing Convergence Proofs for Value and Policy Iteration in Coq
Reinforcement learning algorithms solve sequential decision-making probl...
read it
-
Language as a matrix product state
We propose a statistical model for natural language that begins by consi...
read it
-
Tensor network language model
We propose a new statistical model suitable for machine learning of syst...
read it

Vasily Pestun
is this you? claim profile