LEARNING ACTION SELECTION STRATEGIES IN COMPLEX SOCIAL SYSTEMS

Marco Remondino, Anna Maria Bruno, Nicola Miglietta

2010

Abstract

In this work, a new method for cognitive action selection is formally introduced, keeping into consideration an individual bias for the agents: ego biased learning. It allows the agents to adapt their behaviour according to a payoff coming from the action they performed at time t-1, by converting an action pattern into a synthetic value, updated at each time, but keeping into account their individual preferences towards specific actions. In agent based simulations, the many entities involved usually deal with an action selection based on the reactive paradigm: they usually feature embedded strategies to be used according to the stimuli coming from the environment or other entities. The actors involved in real Social Systems have a local vision and usually can only see their own actions or neighbours’ ones (bounded rationality) and sometimes they could be biased towards a particular behaviour, even if not optimal for a certain situation. Some simulations are run, in order to show the effects of biases, when dealing with an heterogeneous population of agents.

References

  1. Box, H. O., 1984. Primate Behaviour and Social Ecology. London: Chapman and Hall.
  2. Chen M. K., 2008. Rationalization and Cognitive Dissonance: do Choices Affect or Reflect Preferences? Cowles Foundation Discussion Paper No. 1669 Mataric M. J., 2004. Reward Functions for Accelerated Learning. In Proceedings of the Eleventh International Conference on Machine Learning.
  3. Mataric, M. J., 1997. Reinforcement Learning in the Multi-Robot domain. Autonomous Robots, 4(1) Fudenberg, D., and Levine, D. K. 1998. The Theory of Learning in Games. Cambridge, MA: MIT Press Fragaszy, D. and Visalberghi, E., 2001. Recognizing a swan: Socially-biased learning. Psychologia, 44, 82- 98.
  4. Powers R. and Shoham Y., 2005. New criteria and a new algorithm for learning in multi-agent systems. In Proceedings of NIPS.
  5. Sharot T., De Martino B., Dolan R.J., 2009. How Choice Reveals and Shapes Expected Hedonic Outcome. The Journal of Neuroscience, 29(12):3760-3765 Sutton, R. S. and Barto A. G., 1998. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA. A Bradford Book
  6. Watkins, C. J. C. H. 1989. Learning from delayed rewards. PhD thesis, Psychology Department, Univ. of Cambridge.
Download


Paper Citation


in Harvard Style

Remondino M., Maria Bruno A. and Miglietta N. (2010). LEARNING ACTION SELECTION STRATEGIES IN COMPLEX SOCIAL SYSTEMS . In Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-674-022-1, pages 274-281. DOI: 10.5220/0002706802740281


in Bibtex Style

@conference{icaart10,
author={Marco Remondino and Anna Maria Bruno and Nicola Miglietta},
title={LEARNING ACTION SELECTION STRATEGIES IN COMPLEX SOCIAL SYSTEMS},
booktitle={Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2010},
pages={274-281},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002706802740281},
isbn={978-989-674-022-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - LEARNING ACTION SELECTION STRATEGIES IN COMPLEX SOCIAL SYSTEMS
SN - 978-989-674-022-1
AU - Remondino M.
AU - Maria Bruno A.
AU - Miglietta N.
PY - 2010
SP - 274
EP - 281
DO - 10.5220/0002706802740281