arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.04443q-bio.PEcond-mat.stat-mech
收藏

思想种群的随机进化

Stochastic evolution in populations of ideas

Robin Nicole, Peter Sollich, Tobias Galla

摘要:

众所周知,在重复博弈中相互作用的参与者的学习可以被解释为思想群体的进化过程。到目前为止,这些类比大多建立在确定性模型中,学习中的记忆丧失被认为与进化中的突变相似。在这里,我们提出了一个表示的强化学习作为一个随机过程中有限的“人口的想法”。由此产生的生灭动力学具有吸收状态,并允许思想的灭绝或固定,这标志着有限种群中突变选择过程的关键区别。我们描述了几类对称和非对称游戏的思想种群进化的结果。

英文摘要:

It is known that learning of players who interact in a repeated game can be interpreted as an evolutionary process in a population of ideas. These analogies have so far mostly been established in deterministic models, and memory loss in learning has been seen to act similarly to mutation in evolution. We here propose a representation of reinforcement learning as a stochastic process in finite "populations of ideas". The resulting birth-death dynamics has absorbing states and allows for the extinction or fixation of ideas, marking a key difference to mutation-selection processes in finite populations. We characterize the outcome of evolution in populations of ideas for several classes of symmetric and asymmetric games.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑