Learning to Behave Socially
نویسنده
چکیده
Our previous work introduced a methodology for synthesizing and analyzing basic behaviors which served as a substrate for generating a large repertoire of higher{level group interactions (Matari c 1992, Matari c 1993). In this paper we describe how, given the substrate, agents can learn to behave socially, i.e. to maximize average individual by maximizing collective beneet. While this is a well{deened problem for rational agents, it is diicult to learn in situated domains. We describe three sources of reinforcement and show their necessity for learning non{greedy social rules. The learning strategy is demonstrated on a group of physical mobile robots learning to yield and share information in a foraging task.
منابع مشابه
Children's Socio-Emotional Learning Enhanced by Tangibles for Group Activities
Teaching children how to behave socially and how to identify and react to emotions forms the basis of social-emotional learning. So far little research in interaction design has been devoted to tangible interactive objects that can support the scaffolding of children’s socio-emotional learning. This PhD research aims to design and evaluate tangible interactive objects for enhancing children’s s...
متن کاملRunning head: COGNITIVE CONTROL AND SOCIALLY DESIRABLE BEHAVIOR Cognitive Control and Socially Desirable Behavior: The Role of Interpersonal Impact
Individuals’ willingness to act in socially desirable ways, such as sharing resources with others and abiding by norms of ethical conduct, is a necessary condition of social life. The current research reconciles two seemingly contradicting sets of findings on the role of cognitive control in socially desirable behaviors. One set of findings suggests that people are tempted by self-serving impul...
متن کاملPBL-protocols: Guiding and Controlling Problem Based Learning Processes in Virtual Learning Environments
In this paper we describe our approach for supporting the use of the problem-based learning (PBL) method in virtual learning environments. We identify two key difficulties. Firstly, neither learners nor tutors, who are used to more traditional methods of teaching, know exactly what to expect from PBL or how to behave appropriately within their new roles. Secondly, these problems are compounded ...
متن کاملLearning social behavior
This paper discusses the challenges of learning to behave socially in the dynamic, noisy, situated and embodied mobile multi-robot domain. Using the methodology for synthesizing basis behaviors as a substrate for generating a large repertoire of higher-level group !Lnteractions, in this paper we describe how, given the substrate, greedy agents can learn social rules that benefit the group ',as ...
متن کاملSocially-Aware Multiagent Learning: Towards Socially Optimal Outcomes
In multiagent systems the capability of learning is important for an agent to behave appropriately in face of unknown opponents and a dynamic environment. From the system designer’s perspective, it is desirable if the agents can learn to coordinate towards socially optimal outcomes, while also avoiding being exploited by selfish opponents. To this end, we propose a novel gradient ascent based a...
متن کامل