Login / Signup

Teaching Stratego to Play Ball: Optimal Synthesis for Continuous Space MDPs.

Manfred JaegerPeter Gjøl JensenKim Guldstrand LarsenAxel LegaySean SedwardsJakob Haahr Taankvist
Published in: ATVA (2019)
Keyphrases
  • continuous space
  • dynamic programming
  • markov decision processes
  • discrete space
  • reinforcement learning
  • average cost
  • functional programs
  • optimal solution
  • x ray
  • finite horizon