MDP Geometry, Normalization and Value Free Solvers.

Arsenii Mustafin Aleksei Pakharev Alex Olshevsky Ioannis Ch. Paschalidis

Published in: CoRR (2024)

Keyphrases

markov decision processes
three dimensional
reinforcement learning
preprocessing
optimal policy
finite state
state space
sat solvers
markov decision process
sat solving
face recognition
orders of magnitude
geometric information
dynamic programming algorithms