E-HBA:使用行动策略进行专家建议和代理类型化
E-HBA: Using Action Policies for Expert Advice and Agent Typification
摘要:
过去的研究已经研究了两种方法来利用预定义的政策集在重复的互动:作为专家,决定我们自己的行动,并作为类型,模仿其他代理的行为。在这项工作中,我们把这些互补的意见,在一个新的元算法的形式,称为专家HBA(E-HBA),它可以应用于任何专家算法,认为平均(或总)的回报专家在过去产生的。E-HBA逐渐将过去的收益与预测的未来收益混合在一起,这是使用基于类型的特征计算的。我们提出的结果,从一个全面的重复矩阵游戏,比较几个著名的专家算法的性能和没有援助的E-HBA。我们的研究结果表明,E-HBA有可能显着提高专家算法的性能。
英文摘要:
Past research has studied two approaches to utilise predefined policy sets in repeated interactions: as experts, to dictate our own actions, and as types, to characterise the behaviour of other agents. In this work, we bring these complementary views together in the form of a novel meta-algorithm, called Expert-HBA (E-HBA), which can be applied to any expert algorithm that considers the average (or total) payoff an expert has yielded in the past. E-HBA gradually mixes the past payoff with a predicted future payoff, which is computed using the type-based characterisation. We present results from a comprehensive set of repeated matrix games, comparing the performance of several well-known expert algorithms with and without the aid of E-HBA. Our results show that E-HBA has the potential to significantly improve the performance of expert algorithms.
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。