TOWARD SOPHISTICATED AGENT-BASED UNIVERSES - Statements to Introduce some Realistic Features into Classic AI/RL Problems

Filipo Studzinski Perotto

2012

Abstract

In this paper we analyze some common simplifications present in the traditional AI / RL problems. We argue that only facing particular conditions, often avoided in the classic statements, will allow the overcoming of the actual limits of the science, and the achievement of new advances in respect to realistic scenarios. This paper does not propose any paradigmatic revolution, but it presents a compilation of several different elements proposed more or less separately in recent AI research, unifying them by some theoretical reflections, experiments and computational solutions. Broadly, we are talking about scenarios where AI needs to deal with true situatedness agency, providing some kind of anticipatory learning mechanism to the agent in order to allow it to adapt itself to the environment.

References

  1. Boutilier, C.; Dearden, R.; Goldszmidt, M. (2000). Stochastic dynamic programming with factored representations. Artificial Intelligence, Elsevier, v.121.
  2. Degris, T.; Sigaud, O. (2010). Factored Markov Decision Processes. In: Buffet, O; Sigaud, O. (eds.). Markov Decision Processes in Artificial Intelligence. Vandoeuvre-lès-Nancy: Loria.
  3. Feinberg, E. A.; Shwartz, A. (2002). Handbook of Markov Decision Processes: methods and applications. Norwell: Kluwer.
  4. Guestrin, C.; Koller, D.; Parr, R.; Venkataraman, S. (2003). Efficient Solution Algorithms for Factored MDPs. Journal of Artificial Intelligence Research. AAAI Press, v.19.
  5. Hauskrecht, M. (2000). Value-function approximations for partially observable Markov decision processes. Journal of Artificial Intelligence Research, AAAI Press, v.13.
  6. Hansen, E. A.; Feng, Z. (2000). Dynamic programming for POMDPs using a factored state representation. In: Proceedings of 5th AIPS, AAAI Press.
  7. Kaelbling, L. P.; Littman, M. L.; Cassandra, A. R. (1998). Planning and acting in partially observable stochastic domains. Artificial Intelligence, Elsevier, v.101.
  8. Perotto, F. S.; Álvares, L. O. (2007). Incremental Inductive Learning in a Constructivist Agent. In: Proceedings of SGAI-2006. London: Springer-Verlag.
  9. Perotto, F. S.; Álvares, L. O.; Buisson, J.-C. (2007). Constructivist Anticipatory Learning Mechanism (CALM): Dealing with Partially Deterministic and Partially Observable Environments. In: Proceedings of 7th EPIROB, New Jersey: Lund.
  10. Perotto, F. S. (2010). Un Mécanisme Constructiviste d'Apprentissage Automatique d'Anticipations pour des Agents Artificiels Situés. PhD Thesis. Toulouse, France: INP. (in french)
  11. Perotto, F. S. (2012). Anticipatory Learning Mechanisms. In: Encyclopedia of the Sciences of Learning, Springer.
  12. Poupart, P.; Boutilier, C. (2004). VDCBPI: an approximate scalable algorithm for large scale POMDPs. In: Proceedings of 17th NIPS. Cambridge: MIT Press.
  13. Shani, G.; Brafman, R. I.; Shimony, S. E. (2005). ModelBased Online Learning of POMDPs. In: Proceedings of 16th ECML. Berlin: Springer-Verlag. (LNCS 3720).
  14. Sim, H. S.; Kim, K.-E.; Kim, J. H.; Chang, D.-S.; Koo, M.-W. (2008). Symbolic Heuristic Search Value Iteration for Factored POMDPs. In: Proc. of 23rd AAAI, AAAI Press.
  15. Sutton, R. S.; Barto, A. G. (1998). Reinforcement Learning: an introduction. MIT Press.
Download


Paper Citation


in Harvard Style

Studzinski Perotto F. (2012). TOWARD SOPHISTICATED AGENT-BASED UNIVERSES - Statements to Introduce some Realistic Features into Classic AI/RL Problems . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8425-95-9, pages 433-438. DOI: 10.5220/0003835604330438


in Bibtex Style

@conference{icaart12,
author={Filipo Studzinski Perotto},
title={TOWARD SOPHISTICATED AGENT-BASED UNIVERSES - Statements to Introduce some Realistic Features into Classic AI/RL Problems},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2012},
pages={433-438},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003835604330438},
isbn={978-989-8425-95-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - TOWARD SOPHISTICATED AGENT-BASED UNIVERSES - Statements to Introduce some Realistic Features into Classic AI/RL Problems
SN - 978-989-8425-95-9
AU - Studzinski Perotto F.
PY - 2012
SP - 433
EP - 438
DO - 10.5220/0003835604330438