Publications reinforcement learning for pomdps based on action values and stochastic optimization

Reinforcement Learning for POMDPs Based on Action Values and Stochastic Optimization

Reinforcement Learning for POMDPs Based on Action Values and Stochastic Optimization
Theodore J. Perkins, 2002

Download

Abstract

(unavailable)

BibTeX Entry

@InProceedings{Perkins:2002,
  author =       "Perkins, Theodore J.",
  title =        "Reinforcement Learning for {POMDP}s Based on Action Values and Stochastic Optimization",
  booktitle =    "Proceedings of the Eighteenth National Conference on Artificial Intelligence and Fourteenth Conference on Innovative Applications of Artificial Intelligence (AAAI/IAAI 2002)",
  year =         "2002",
  publisher = "AAAI Press",
  pages =     "199--204",
  url = "https://www.aaai.org/Papers/AAAI/2002/AAAI02-031.pdf",
  bib2html_rescat = "Partial Observability",
}