1 / 12

Emergence of Norms through Social Learning

Emergence of Norms through Social Learning. Partha Mukherjee, Sandip Sen and St éphane Airiau Mathematical and Computer Sciences Department University of Tulsa, Oklahoma, USA. Introduction .

livia
Download Presentation

Emergence of Norms through Social Learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Emergence of Norms through Social Learning Partha Mukherjee, Sandip Sen and Stéphane Airiau Mathematical and Computer Sciences Department University of Tulsa, Oklahoma, USA IJCAI’07

  2. Introduction Norm: “a convention as an equilibrium that everyone expects in interactions that have more than one equilibrium” [Young, 1996] Use a population of learning agents to simulate a population that faces a problem modeled by a game and study the emergence of norms ALAg-07

  3. Example of a norm: picking the side of the road R L Agents need to decide on one of several equally desirable alternatives. This game can be extended to m actions L R ALAg-07

  4. Previous Work • Previous work on learning norms assume observation of other interactions between agents. How norms will emerge if all interactions were private? • Social Learning (IJCAI-07): agents play a bimatrix game, at each interaction, an agent plays against another agent, taken at random, in the population Empirical study: Study effect of population size, number of actions available, effect of learning algorithms, presence of non-learning agents, multiple relatively isolated populations ALAg-07

  5. Social Learning • Population of Nlearning agents • A 2-player, k-action gameM • M is common knowledge • Each agent has a learning algorithm (fixed, intrinsic) to play M as a row or a column player • Repeatedly, agents play the game M against an unknown, random opponent. ALAg-07

  6. Protocol of play For each iteration, for each agent • Pick randomly one agent in its neighborhood • For each pair, one agent is randomly considered row, the other column player • Each agent pick an action, and can observe only the action of the other agent constituting the pair • Each agent gets the reward accordingly, and updates its learning mechanism ALAg-07

  7. Interactions are limited to neighboring agents ALAg-07

  8. Effect of neighboring size ALAg-07

  9. Learning Dynamics D=1 D=15 It 145 It 355 It 480 ALAg-07  Driving on the left Driving on the right

  10. Influence of non-learners Non-learners use identical strategiesD=5 ALAg-07

  11. Influence of non-learnersUsing different strategies D=1 D=15 It 905 It 45 It 535 ALAg-07  Driving on the left Driving on the right

  12. Conclusion • Bottom up process for the emergence of social norms • Depends only on private expertise • Agents can learn and sustain useful social norms • Agent population with smaller neighborhoods converge faster to a norm ALAg-07

More Related