On Measuring Social Intelligence: Experiments on Competition and Cooperation

Insa-Cabrera, Javier; Benacloch-Ayuso, Jose-Luis; Hernández-Orallo, José

doi:10.1007/978-3-642-35506-6_14

Cited by 11 publications

(11 citation statements)

References 11 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers, also said that when we win cooperation of others and get along well with them, we are showing traits of social intelligence. To sum up we can say social intelligence is a trait which is affected by various ecological variables (Thakur et al, 2013;Insa-Cabrera et al, 2012). Social Intelligence can also be said as the traditional wisdom we possess or the modern-day smartness required to deal various situations.…”

Section: Social Intelligencementioning

confidence: 99%

The Relevance of Social Intelligence for Effective Optimization of Retirement and Successful Ageing

Sanwal

Sareen

2021

Ageing Int

View full text Add to dashboard Cite

Section: Social Intelligencementioning

confidence: 99%

The Relevance of Social Intelligence for Effective Optimization of Retirement and Successful Ageing

Sanwal

Sareen

2021

Ageing Int

View full text Add to dashboard Cite

“…Finally, the information-theoretic approach is not isolated from some of the approaches seen so far in section 2. Actually, some hybridisations and integrated approaches have been proposed [74,43,78,77,90] (apart from the compression-enriched Turing Tests ( [39,40] already mentioned above). Figure 7 shows the fragmentation of the approaches seen in previous sections.…”

Section: Evaluation Using Aitmentioning

confidence: 99%

Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement

Hernández-Orallo

2016

Artif Intell Rev

Self Cite

108

View full text Add to dashboard Cite

The evaluation of artificial intelligence systems and components is crucial for the progress of the discipline. In this paper we describe and critically assess the different ways AI systems are evaluated, and the role of components and techniques in these systems. We first focus on the traditional task-oriented evaluation approach. We identify three kinds of evaluation: human discrimination, problem benchmarks and peer confrontation. We describe some of the limitations of the many evaluation schemes and competitions in these three categories, and follow the progression of some of these tests. We then focus on a less customary (and challenging) ability-oriented evaluation approach, where a system is characterised by its (cognitive) abilities, rather than by the tasks it is designed to solve. We discuss several possibilities: the adaptation of cognitive tests used for humans and animals, the development of tests derived from algorithmic information theory or more integrated approaches under the perspective of universal psychometrics. We analyse some evaluation tests from AI that are better positioned for an ability-oriented evaluation and discuss how their problems and limitations can possibly be addressed with some of the tools and ideas that appear within the paper. Finally, we enumerate a series of lessons learnt and generic guidelines to be used when an AI evaluation scheme is under consideration.

show abstract

“…In games (and multi-agent systems in general), the difficulty of a problem depends on the rules, but most especially on the opponents. For general multiagent systems and multi-agent reinforcement learning [9] in particular (and their competitions [24]), the difficulty of the system depends on the opponents and cooperators [41], and their intelligence [35,37]. In fact, some environments may have a rich, sensitive behaviour with some agents, but can have a very different, chaotic (or unresponsive) behaviour with other agents.…”

Section: Looking At Other (Competing) Agentsmentioning

confidence: 99%

On environment difficulty and discriminating power

Hernández-Orallo

2014

Auton Agent Multi-Agent Syst

Self Cite

View full text Add to dashboard Cite

This paper presents a way to estimate the difficulty and discriminating power of any task instance. We focus on a very general setting for tasks: interactive (possibly multi-agent) environments where an agent acts upon observations and rewards. Instead of analysing the complexity of the environment, the state space or the actions that are performed by the agent, we analyse the performance of a population of agent policies against the task, leading to a distribution that is examined in terms of policy complexity. This distribution is then sliced by the algorithmic complexity of the policy and analysed through several diagrams and indicators. The notion of environment response curve is also introduced, by inverting the performance results into an ability scale. We apply all these concepts, diagrams and indicators to two illustrative problems: a class of agent-populated elementary cellular automata, showing how the difficulty and discriminating power may vary for several environments, and a multi-agent system, where agents can become predators or preys, and may need to coordinate. Finally, we discuss how these tools can be applied to characterise (interactive) tasks and (multi-agent) environments. These characterisations can then be used to get more insight about agent performance and to facilitate the development of adaptive tests for the evaluation of agent abilities.

show abstract

On Measuring Social Intelligence: Experiments on Competition and Cooperation

Cited by 11 publications

References 11 publications

The Relevance of Social Intelligence for Effective Optimization of Retirement and Successful Ageing

The Relevance of Social Intelligence for Effective Optimization of Retirement and Successful Ageing

Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement

On environment difficulty and discriminating power

Contact Info

Product

Resources

About