Learning with repeated-game strategies
نویسندگان
چکیده
We use the self-tuning Experience Weighted Attraction model with repeated-game strategies as a computer testbed to examine the relative frequency, speed of convergence and progression of a set of repeated-game strategies in four symmetric 2 × 2 games: Prisoner's Dilemma, Battle of the Sexes, Stag-Hunt, and Chicken. In the Prisoner's Dilemma game, we find that the strategy with the most occurrences is the "Grim-Trigger." In the Battle of the Sexes game, a cooperative pair that alternates between the two pure-strategy Nash equilibria emerges as the one with the most occurrences. In the Stag-Hunt and Chicken games, the "Win-Stay, Lose-Shift" and "Grim-Trigger" strategies are the ones with the most occurrences. Overall, the pairs that converged quickly ended up at the cooperative outcomes, whereas the ones that were extremely slow to reach convergence ended up at non-cooperative outcomes.
منابع مشابه
A generalized approach to belief learning in repeated games
We propose a methodology that is generalizable to a broad class of repeated games in order to facilitate operability of belief learning models with repeated-game strategies. The methodology consists of (1) a generalized repeated-game strategy space, (2) a mapping between histories and repeated-game beliefs, and (3) asynchronous updating of repeated-game strategies. We implement the proposed met...
متن کاملOnline Learning with Variable Stage Duration
We consider online learning in repeated decision problems, within the framework of a repeated game against an arbitrary opponent. For repeated matrix games, well known results establish the existence of no-regret strategies; such strategies secure a long-term average payoff that comes close to the maximal payoff that could be obtained, in hindsight, by playing any fixed action against the obser...
متن کاملThe effect of using computer games on learning free throw Basketball skill and comparison with skilled and learning pattern
The aim of this experiment was to study the effect of computer game on acquisition and retention of free throw basketball skills (accuracy and pattern) and compare this method with two patterning methods (skilled and learning). 50 high school students age range 15-17 years were selected as a research samples. Subjects after participating in the pretest were divided into 5 equal groups and each ...
متن کاملLearning Strategies
Adaptive learning models that have been tested against experimental data typically share two features: (i) initial attractions (or beliefs) are given exogenously, and (ii) learning is based on the performance of stage-game actions rather than repeated game strategies. We develop a model of learning which endogenizes initial attractions and allows for the learning of repeated game strategies. Le...
متن کاملLearning and teaching in repeated games: A machine learning approach to long-term best-response play
Repeated games and long-term best-response play. We consider the problem of learning during a play of a a repeated game. Existing approaches often focus on algorithms that asymptotically achieve an equilibrium of the one-shot game. We shift away from that paradigm to consider learning strategies that attempt to play long-term best-response to the opponent’s observed strategy. This goal may be m...
متن کاملComparison of the effectiveness of Fernald\'s multisensory training and computer game training on dyslexia in elementary students with learning disabilities
Purpose: The aim of this study was to compare the effectiveness of Fernaldchr(chr('39')39chr('39'))s multisensory training and computer game training on dyslexia in primary school students with learning disabilities in Ahvaz. Methodology: This study was applied in terms of purpose and in an experimental framework (pre-test-post-test design with control group). The statistical population in the...
متن کامل