Zobrazeno 1 - 1
of 1
pro vyhledávání: '"de Brusse, Jonathan"'
Given a discounted cost, we study deterministic discrete-time systems whose inputs are generated by policy iteration (PI). We provide novel near-optimality and stability properties, while allowing for non stabilizing initial policies. That is, we fir
Externí odkaz:
http://arxiv.org/abs/2403.19007