Statistical-mechanics approach to a reinforcement learning model with memory

Details Statistical-mechanics approach to a reinforcement learning model with memory Statistical-mechanics approach to a reinforcement learning model with memory

2008-04-04

arxiv.org/abs/0804.0742v3

Physica A vol. 388 (2009) pp. 1849-1856

Physics

Condensed Matter

Statistical Mechanics

6 pages, some additional numerical calculations

Scientific paper

10.1016/j.physa.2009.01.028

We introduce a two-player model of reinforcement learning with memory. Past actions of an iterated game are stored in a memory and used to determine player's next action. To examine the behaviour of the model some approximate methods are used and confronted against numerical simulations and exact master equation. When the length of memory of players increases to infinity the model undergoes an absorbing-state phase transition. Performance of examined strategies is checked in the prisoner' dilemma game. It turns out that it is advantageous to have a large memory in symmetric games, but it is better to have a short memory in asymmetric ones.

Affiliated with

Also associated with

No associations

Rating

Statistical-mechanics approach to a reinforcement learning model with memory does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Statistical-mechanics approach to a reinforcement learning model with memory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical-mechanics approach to a reinforcement learning model with memory will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-191056