Co-evolution of cooperation in a pursuit evasion game

Nitschke, Geoff

doi:10.1109/iros.2003.1248964

Cited by 15 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many authors have investigated variants of the "predator-prey" task [77,63,140,64,65,29,148,28,139], sometimes called "pursuitevasion" [122,32,33,136]. In this task, a population of Khepera robots, the prey, interact by tournaments with other Khepera robots, the predators.…”

Section: Task Agnosticmentioning

confidence: 99%

See 1 more Smart Citation

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

Evolutionary robotics is often viewed as the application of a family of black-box optimization algorithms -evolutionary algorithms -to the design of robots, or parts of robots. When considering evolutionary robotics as black-box optimization, the selective pressure is mainly driven by a user-defined, black-box fitness function, and a domain-independent selection procedure. However, most evolutionary robotics experiments face similar challenges in similar setups: the selective pressure, and, in particular, the fitness function, is not a pure user-defined black box. The present review shows that, because evolutionary robotics experiments share common features, selective pressures for evolutionary robotics are a subject of research on their own. The literature has been split into two categories: goal refiners, aimed at changing the definition of a good solution, and process helpers, designed to help the search process. Two subcategories are further considered: task-specific approaches, which require knowledge on how to solve the task and taskagnostic ones, which do not need it. Besides highlighting the diversity of the approaches and their respective goals, the present review shows that many task-agnostic process helpers have been proposed during the last years, thus bringing us closer to the goal of a fully automated robot behavior design process.

show abstract

Section: Task Agnosticmentioning

confidence: 99%

“…Behavior-based speciation [175][176][177] • • Behavioral diversity [129,143,51,124,52,131,145] • • Co-evolution environment/controllers [158,10,9] • • Competitive co-evolution [33,28,172,77,29,65,122,136,139,32,170,140,178,62,64,63,135,148] • Table 2. Process helpers.…”

Section: Task-agnosticmentioning

confidence: 99%

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

show abstract

“…There are different artificial approaches of competitive evolution applied in pursuit domain; single pool approach, plasticity approach and multiple pools approach. A system of robots uses a single genotype illustrates a single pool approach, a system of robots uses learning mechanism characterizes plasticity approach and multiple pools approach is used for robots that share different genotypes (Nitschke, 2003). Floreano et al appraised a competitive evolutionary of cooperation in predator-pray scenario by using two mobile robots in evolutionary robotics experiments.…”

Section: Evolution Of Cooperationmentioning

confidence: 99%

“…G. Nitschke employed cooperative co-evolution in his research of pursuit evasion game. Briefly, His research is about a team of three robots "pursuers" cooperating to halt one of other three robots "evaders" (Nitschke, 2003). He used the multiple pools competitive evolution approach and yielded great performance compared with single pool and plasticity approaches.…”

Section: Evolution Of Cooperationmentioning

confidence: 99%

Multi-Agent System Concepts Theory and Application Phases

Al-Jumaily¹

2006

Mobile Robotics, Moving Intelligence

View full text Add to dashboard Cite

“…The use of specific environments (such as predator-prey, cooperation games, etc. [27,83,28]) ensures that some predefined social behaviours appear, but their generality is questionable and agent performance may depend on the specialisation to the game (good predators, good preys, etc.) instead of general social capabilities.…”

Section: Introductionmentioning

confidence: 99%

Towards a Universal Test of Social Intelligence

Cabrera¹

View full text Add to dashboard Cite

Under the view of artificial intelligence, an intelligent agent is an autonomous entity which interacts in an environment through observations and actions, trying to achieve one or more goals with the aid of several signals called rewards. The creation of intelligent agents is proliferating during the last decades, and the evaluation of their intelligence is a fundamental issue for their understanding, construction and improvement.Social intelligence is recently obtaining special attention in the creation of intelligent agents due to the current view of human intelligence as highly social. Social intelligence in natural and artificial systems is usually measured by the evaluation of associated traits or tasks that are deemed to represent some facets of social behaviour. The amalgamation of these traits or tasks is then used to configure an operative notion of social intelligence. However, this operative notion does not truly represent what social intelligence is and a definition following this principle will not be precise. Instead, in this thesis we investigate the evaluation of social intelligence in a more formal and general way, by actually considering the evaluee's interaction with other agents.In this thesis we analyse the implications of evaluating social intelligence using a test that evaluates general intelligence. For this purpose, we include other agents into an initially singleagent environment to figure out the issues that appear when evaluating an agent in the context of other agents. From this analysis we obtain useful information for the evaluation of social intelligence.From the lessons learned, we identify the components that should be considered in order to measure social intelligence, and we provide a formal and parametrised definition of social intelligence. This definition calculates an agent's social intelligence as its expected performance in a set of environments with a set of other agents arranged in teams and participating in lineups, with rewards being re-understood appropriately. This is conceived as a tool to define social intelligence testbeds where we can generate several degrees of competitive and cooperative behaviours. We test this definition by experimentally analysing the influence of teams and agent line-ups for several multi-agent systems with variants of Q-learning agents.However, not all testbeds are appropriate for the evaluation of social intelligence. To facilitate the analysis of a social intelligence testbed, we provide some formal property models about social intelligence in order to characterise the testbed and thus assess its suitability. Finally, we use the presented properties to characterise some social games and multi-agent environments, we make a comparison between them and discuss their strengths and weaknesses in order to evaluate social intelligence.ii ResumenBajo la visión de la inteligencia artificial, un agente inteligente es una entidad autónoma la cual interactúa en un entorno a través de observaciones y acciones, tratando de lograr uno o más ...

show abstract

Co-evolution of cooperation in a pursuit evasion game

Cited by 15 publications

References 13 publications

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Multi-Agent System Concepts Theory and Application Phases

Towards a Universal Test of Social Intelligence

Contact Info

Product

Resources

About