Learning Agents in a Homo Egualis Society
نویسندگان
چکیده
ABSTRACT Coordination is an important issue in multi-agent systems. A possible approa h to ta kle oordination, that re ently reeived quite a lot of attention, is to learn the e e ts of intera tion in the joint a tion spa e. However joint a tion spa es violate generally a epted requirements of multi-agents systems, su h as : distributed ontrol, asyn hronous a tions, in omplete information, ost of ommuni ation. Moreover we argue that on top of the drawba ks of joint a tion spa es, basi problems still remain unsolved. In this paper we propose an approa h based on human so iality. In parti ular, we investigate a Homo egualis setting inspired on anthropology. As shown in the paper Homo egualis results in a periodi al poli y that is fair to all agents involved and that results in an optimal solution with respe t to the global goal. keywords: multi agent oordination homo egualis reinfor ement learning periodi poli ies.
منابع مشابه
The Practical Use of ESRL For Conflicting Interest Games
In this paper we tested the practical use of an existing learning algorithm, called Exploring Selfish Reinforcement Learning (ESRL), on conflicting interest games. This algorithm is based on the principles of learning automata and, for games where agents have conflicting interests, on a Homo egualis society. Furthermore we propose some variations on the exploration heuristic of the algorithm an...
متن کاملArtificial agents learning human fairness
Recent advances in technology allow multi-agent systems to be deployed in cooperation with or as a service for humans. Typically, those systems are designed assuming individually rational agents, according to the principles of classical game theory. However, research in the field of behavioral economics has shown that humans are not purely self-interested: they strongly care about fairness. The...
متن کاملProactive Resource Management in LTE-U Systems: A Deep Learning Perspective
LTE in unlicensed spectrum (LTE-U) is a promising approach to overcome the wireless spectrum scarcity. However, to reap the benefits of LTE-U, a fair coexistence mechanism with other incumbent WiFi deployments is required. In this paper, a novel deep learning approach is proposed for modeling the resource allocation problem of LTE-U small base stations (SBSs). The proposed approach enables mult...
متن کاملHierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملAssembly of an antiparallel homo-adenine DNA duplex by small-molecule binding.
Molecules that reversibly bind DNA and trigger the formation of non-Watson-Crick secondary structures would be useful in the design of dynamic DNA nanostructures and as potential leads for new therapeutic agents. We demonstrate that coralyne, a small crescent-shaped molecule, promotes the formation of a duplex secondary structure from homo-adenine oligonucleotides. AFM studies reveal that the s...
متن کامل