On Measuring Social Intelligence: Experiments on Competition and Cooperation
Evaluating agent intelligence is a fundamental issue for the understanding, construction and improvement of autonomous agents. New intelligence tests have been recently developed based on an assessment of task complexity using algorithmic information theory. Some early experimental results have shown that these intelligence tests may be able to distinguish between agents of the same kind, but they do not place very different agents, e.g., humans and machines, on a correct scale. It has been suggested that a possible explanation is that these tests do not measure social intelligence. One formal approach to incorporate social environments in an intelligence test is the recent notion of Darwin-Wallace distribution. Inspired by this distribution we present several new test settings considering competition and cooperation, where we evaluate the “social intelligence” of several reinforcement learning algorithms. The results show that evaluating social intelligence.
KeywordsMultiagent System Intelligence Test Kolmogorov Complexity Evolutionary Game Theory Social Intelligence
Unable to display preview. Download preview PDF.
- 1.Dowe, D.L., Hajek, A.R.: A computational extension to the Turing Test. In: Proceedings of the 4th Conference of the Australasian Cognitive Science Society, University of Newcastle, NSW, Australia (September 1997)Google Scholar
- 3.Hernández-Orallo, J.: A (hopefully) non-biased universal environment class for measuring intelligence of biological and artificial systems. In: Hutter, M., et al. (eds.) 3rd Intl Conf. on Artificial General Intelligence, pp. 182–183. Atlantis Press (2010)Google Scholar
- 5.Hernández-Orallo, J., Dowe, D.L., España-Cubillo, S., Hernández-Lloreda, M.V., Insa-Cabrera, J.: On More Realistic Environment Distributions for Defining, Evaluating and Developing Intelligence. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS (LNAI), vol. 6830, pp. 82–91. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 6.Hernández-Orallo, J., Minaya-Collado, N.: A formal definition of intelligence based on an intensional variant of Kolmogorov complexity. In: Proc. Intl Symposium of Engineering of Intelligent Systems, EIS 1998, La Laguna, Spain, pp. 146–163. ICSC Press (February 1998)Google Scholar
- 8.Kaisers, M., Tuyls, K.: Frequency adjusted multi-agent Q-learning. In: Proc. 9th Intl Conf. on Autonomous Agents and Multiagent Systems, pp. 309–316 (2010)Google Scholar
- 10.Li, M., Vitányi, P.: An introduction to Kolmogorov complexity and its applications, 3rd edn. Springer (2008)Google Scholar
- 11.Rummery, G., Niranjan, M.: On-line Q-learning using connectionist systems. Cambridge University Engineering Department, TR 166 (1994)Google Scholar
- 12.Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. The MIT Press (1998)Google Scholar
- 14.Weibull, J.: Evolutionary game theory. The MIT Press (1997)Google Scholar
- 15.Wiering, M.: QV (λ)-learning: A new on-policy reinforcement learning algorithm. In: 7th European Ws. on Reinforcement Learning, pp. 17–18 (2005)Google Scholar