Login / Signup

Good-for-MDPs Automata for Probabilistic Analysis and Reinforcement Learning.

Ernst Moritz HahnMateo PerezSven ScheweFabio SomenziAshutosh TrivediDominik Wojtczak
Published in: TACAS (1) (2020)
Keyphrases
  • reinforcement learning
  • state space
  • markov decision processes
  • statistical analysis
  • dynamic programming
  • generative model
  • optimal policy
  • mobile robot
  • least squares
  • infinite horizon