Almost-rational learning of Nash equilibrium without absolute continuity
If players learn to play an infinitely repeated game using Bayesian learning, it is known that their strategies eventually approximate Nash equilibria of the repeated game under an absolute-continuity assumption on their prior beliefs. We suppose here that Bayesian learners do not start with such a...
| Main Author: | |
|---|---|
| Format: | Working paper |
| Published: |
University of Oxford
2012
|
| _version_ | 1797081883697217536 |
|---|---|
| author | Norman, T |
| author_facet | Norman, T |
| author_sort | Norman, T |
| collection | OXFORD |
| description | If players learn to play an infinitely repeated game using Bayesian learning, it is known that their strategies eventually approximate Nash equilibria of the repeated game under an absolute-continuity assumption on their prior beliefs. We suppose here that Bayesian learners do not start with such a "grain of truth", but with arbitrarily low probability they revise beliefs that are performing badly. We show that this process converges in probability to a Nash equilibrium of the repeated game. |
| first_indexed | 2024-03-07T01:20:21Z |
| format | Working paper |
| id | oxford-uuid:9019b4e7-4faf-40be-8ab4-ec23e380b2b0 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T01:20:21Z |
| publishDate | 2012 |
| publisher | University of Oxford |
| record_format | dspace |
| spelling | oxford-uuid:9019b4e7-4faf-40be-8ab4-ec23e380b2b02022-03-26T23:09:15ZAlmost-rational learning of Nash equilibrium without absolute continuityWorking paperhttp://purl.org/coar/resource_type/c_8042uuid:9019b4e7-4faf-40be-8ab4-ec23e380b2b0Bulk import via SwordSymplectic ElementsUniversity of Oxford2012Norman, TIf players learn to play an infinitely repeated game using Bayesian learning, it is known that their strategies eventually approximate Nash equilibria of the repeated game under an absolute-continuity assumption on their prior beliefs. We suppose here that Bayesian learners do not start with such a "grain of truth", but with arbitrarily low probability they revise beliefs that are performing badly. We show that this process converges in probability to a Nash equilibrium of the repeated game. |
| spellingShingle | Norman, T Almost-rational learning of Nash equilibrium without absolute continuity |
| title | Almost-rational learning of Nash equilibrium without absolute continuity |
| title_full | Almost-rational learning of Nash equilibrium without absolute continuity |
| title_fullStr | Almost-rational learning of Nash equilibrium without absolute continuity |
| title_full_unstemmed | Almost-rational learning of Nash equilibrium without absolute continuity |
| title_short | Almost-rational learning of Nash equilibrium without absolute continuity |
| title_sort | almost rational learning of nash equilibrium without absolute continuity |
| work_keys_str_mv | AT normant almostrationallearningofnashequilibriumwithoutabsolutecontinuity |