scholarly journals Human-agent coordination in a group formation game

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuomas Takko ◽  
Kunal Bhattacharya ◽  
Daniel Monsivais ◽  
Kimmo Kaski
Keyword(s):  
Decision Making ◽  
Autonomous Agents ◽  
Human Subjects ◽  
Group Formation ◽  
Small World ◽  
Human Agent ◽  
Human Decision ◽  
Overall Performance ◽  
Behaviour Changes ◽  
Formation Game

AbstractCoordination and cooperation between humans and autonomous agents in cooperative games raise interesting questions on human decision making and behaviour changes. Here we report our findings from a group formation game in a small-world network of different mixes of human and agent players, aiming to achieve connected clusters of the same colour by swapping places with neighbouring players using non-overlapping information. In the experiments the human players are incentivized by rewarding to prioritize their own cluster while the model of agents’ decision making is derived from our previous experiment of purely cooperative game between human players. The experiments were performed by grouping the players in three different setups to investigate the overall effect of having cooperative autonomous agents within teams. We observe that the human subjects adjust to autonomous agents by being less risk averse, while keeping the overall performance efficient by splitting the behaviour into selfish and cooperative actions performed during the rounds of the game. Moreover, results from two hybrid human-agent setups suggest that the group composition affects the evolution of clusters. Our findings indicate that in purely or lesser cooperative settings, providing more control to humans could help in maximizing the overall performance of hybrid systems.

scholarly journals Predicting human decision making in psychological tasks with recurrent neural networks

2021 ◽  
Author(s):  
Baihan Lin ◽  
Djallel Bouneffouf ◽  
Guillermo Cecchi
Keyword(s):  
Decision Making ◽  
Time Series ◽  
Prisoner's Dilemma ◽  
Iowa Gambling Task ◽  
Human Subjects ◽  
Prisoner’S Dilemma ◽  
Gambling Task ◽  
Iterated Prisoner's Dilemma ◽  
Human Decision ◽  
Iterated Prisoner’S Dilemma

Unlike traditional time series, the action sequences of human decision making usually involve many cognitive processes such as beliefs, desires, intentions and theory of mind, i.e. what others are thinking. This makes predicting human decision making challenging to be treated agnostically to the underlying psychological mechanisms. We propose to use a recurrent neural network architecture based on long short-term memory networks (LSTM) to predict the time series of the actions taken by the human subjects at each step of their decision making, the first application of such methods in this research domain. In this study, we collate the human data from 8 published literature of the Iterated Prisoner's Dilemma comprising 168,386 individual decisions and postprocess them into 8,257 behavioral trajectories of 9 actions each for both players. Similarly, we collate 617 trajectories of 95 actions from 10 different published studies of Iowa Gambling Task experiments with healthy human subjects. We train our prediction networks on the behavioral data from these published psychological experiments of human decision making, and demonstrate a clear advantage over the state-of-the-art methods in predicting human decision making trajectories in both single-agent scenarios such as the Iowa Gambling Task and multi-agent scenarios such as the Iterated Prisoner's Dilemma. In the prediction, we observe that the weights of the top performers tends to have a wider distribution, and a bigger bias in the LSTM networks, which suggests possible interpretations for the distribution of strategies adopted by each group.

scholarly journals Group formation on a small-world: experiment and modelling

2019 ◽  
Vol 16 (156) ◽  
pp. 20180814 ◽  
Author(s):  
Kunal Bhattacharya ◽  
Tuomas Takko ◽  
Daniel Monsivais ◽  
Kimmo Kaski
Keyword(s):  
Group Formation ◽  
Small World ◽  
Limited Information ◽  
Online Game ◽  
Probability Matching ◽  
Agent Based ◽  
Human Agent ◽  
Neighbourhood Information ◽  
Human Participants ◽  
Parameter Ranges

As a step towards studying human-agent collectives, we conduct an online game with human participants cooperating on a network. The game is presented in the context of achieving group formation through local coordination. The players set initially to a small-world network with limited information on the location of other players, coordinate their movements to arrange themselves into groups. To understand the decision-making process, we construct a data-driven model of agents based on probability matching. The model allows us to gather insight into the nature and degree of rationality employed by the human players. By varying the parameters in agent-based simulations, we are able to benchmark the human behaviour. We observe that while the players use the neighbourhood information in limited capacity, the perception of risk is optimal. We also find that for certain parameter ranges, the agents are able to act more efficiently when compared to the human players. This approach would allow us to simulate the collective dynamics in games with agents having varying strategies playing alongside human proxies.

A Computational Role for Dopamine Delivery in Human Decision-Making

1998 ◽  
Vol 10 (5) ◽  
pp. 623-630 ◽  
Author(s):  
David M. Egelman ◽  
Christophe Person ◽  
P. Read Montague
Keyword(s):  
Decision Making ◽  
Human Subjects ◽  
Neural Mechanisms ◽  
Behavioral Strategies ◽  
Pharmacological Interventions ◽  
Decision Strategies ◽  
Human Decision ◽  
Future Events ◽  
New Interpretation ◽  
Mesencephalic Dopamine

Recent work suggests that fluctuations in dopamine delivery at target structures represent an evaluation of future events that can be used to direct learning and decision-making. To examine the behavioral consequences of this interpretation, we gave simple decision-making tasks to 66 human subjects and to a network based on a predictive model of mesencephalic dopamine systems. The human subjects displayed behavior similar to the network behavior in terms of choice allocation and the character of deliberation times. The agreement between human and model performances suggests a direct relationship between biases in human decision strategies and fluctuating dopamine delivery. We also show that the model offers a new interpretation of deficits that result when dopamine levels are increased or decreased through disease or pharmacological interventions. The bottom-up approach presented here also suggests that a variety of behavioral strategies may result from the expression of relatively simple neural mechanisms in different behavioral contexts.

A MODEL OF GRAPH COLORING DYNAMICS WITH ATTENTION WAVES AND STRATEGIC WAITING

2009 ◽  
Vol 12 (06) ◽  
pp. 549-564 ◽  
Author(s):  
BORISLAV HADZHIEV ◽  
KATJA WINDT ◽  
WERNER BERGHOLZ ◽  
MARC-THORSTEN HÜTT
Keyword(s):  
Graph Coloring ◽  
Autonomous Agents ◽  
Human Subjects ◽  
Small World ◽  
Organizational Structures ◽  
Strong Increase ◽  
Avoidance Task ◽  
Surprising Result ◽  
Coloring Problem ◽  
Run Time

Recently, Kearns et al. [Kearns, M., Suri, S. and Montfort, N., An experimental study of the coloring problem on human subject networks, Science313 (2006) 824–827] studied the topology dependence of graph coloring dynamics. In their empirical study, the authors analyze, how a network of human subjects acting as autonomous agents performs in solving a conflict-avoidance task (the graph coloring problem) for different network architectures. A surprising result was that the run-time of the empirical dynamics decreases with the number of shortcuts in a Watts–Strogatz small-world graph. In a simulation of the dynamics based on randomly selecting color conflicts for update, they observe a strong increase of the run-time with the number of shortcuts. Here, we propose classes of strategies, which are capable of explaining the decrease in run-time with an increasing number of shortcuts. We show that the agent's strategy, the graph topology, and the complexity of the problem (essentially given by the graph's chromatic number) interact nontrivially yielding unexpected insights into the problem-solving capacity of organizational structures.

scholarly journals Achieving Closed-Loop Control Simulation of Human-Artefact Interaction: A Comparative Review

2011 ◽  
Vol 2011 ◽  
pp. 1-16 ◽  
Author(s):  
Wilhelm Frederik van der Vegte ◽  
Imre Horváth
Keyword(s):  
Decision Making ◽  
Human Subjects ◽  
Low Cost ◽  
Simulation Models ◽  
Level Control ◽  
User Interactions ◽  
Loop Control ◽  
Low Level ◽  
Comparative Review ◽  
Human Decision

To include user interactions in simulations of product use, the most common approach is to couple human subjects to simulation models, using hardware interfaces to close the simulation-control loop. Testing with virtual human models could offer a low-cost addition to evaluation with human subjects. This paper explores the possibilities for coupling human and artefact models to achieve fully software-based interaction simulations. We have critically reviewed existing partial solutions to simulate or execute control (both human control and product-embedded control) and compared solutions from literature with a proof-of-concept we have recently developed. Our concept closes all loops, but it does not rely on validated algorithms to predict human decision making and low-level human motor control. For low-level control, validated solutions are available from other approaches. For human decision making, however, validated algorithms exist only to predict the timing but not the reasoning behind it. To identify decision-making schemes beyond what designers can conjecture, testing with human subjects remains indispensable.

scholarly journals Studying Collective Human Decision Making and Creativity with Evolutionary Computation

2015 ◽  
Vol 21 (3) ◽  
pp. 379-393 ◽  
Author(s):  
Hiroki Sayama ◽  
Shelley D. Dionne
Keyword(s):  
Decision Making ◽  
Evolutionary Computation ◽  
Interdisciplinary Research ◽  
Collaborative Design ◽  
Social Dynamics ◽  
Human Subjects ◽  
Computational Simulation ◽  
Idea Generation ◽  
Evolutionary Perspective ◽  
Human Decision

We report a summary of our interdisciplinary research project “Evolutionary Perspective on Collective Decision Making” that was conducted through close collaboration between computational, organizational, and social scientists at Binghamton University. We redefined collective human decision making and creativity as evolution of ecologies of ideas, where populations of ideas evolve via continual applications of evolutionary operators such as reproduction, recombination, mutation, selection, and migration of ideas, each conducted by participating humans. Based on this evolutionary perspective, we generated hypotheses about collective human decision making, using agent-based computer simulations. The hypotheses were then tested through several experiments with real human subjects. Throughout this project, we utilized evolutionary computation (EC) in non-traditional ways—(1) as a theoretical framework for reinterpreting the dynamics of idea generation and selection, (2) as a computational simulation model of collective human decision-making processes, and (3) as a research tool for collecting high-resolution experimental data on actual collaborative design and decision making from human subjects. We believe our work demonstrates untapped potential of EC for interdisciplinary research involving human and social dynamics.

Cognitive Process of Moral Decision-Making for Autonomous Agents

2013 ◽  
Vol 5 (4) ◽  
pp. 61-76 ◽  
Author(s):  
José-Antonio Cervantes ◽  
Luis-Felipe Rodríguez ◽  
Sonia López ◽  
Félix Ramos ◽  
Francisco Robles
Keyword(s):  
Decision Making ◽  
Intelligent Systems ◽  
Computational Models ◽  
Autonomous Agents ◽  
Empirical Studies ◽  
Theoretical Models ◽  
Moral Decision ◽  
Moral Decision Making ◽  
Biologically Inspired ◽  
Human Decision

There are a great variety of theoretical models of cognition whose main purpose is to explain the inner workings of the human brain. Researchers from areas such as neuroscience, psychology, and physiology have proposed these models. Nevertheless, most of these models are based on empirical studies and on experiments with humans, primates, and rodents. In fields such as cognitive informatics and artificial intelligence, these cognitive models may be translated into computational implementations and incorporated into the architectures of intelligent autonomous agents (AAs). Thus, the main assumption in this work is that knowledge in those fields can be used as a design approach contributing to the development of intelligent systems capable of displaying very believable and human-like behaviors. Decision-Making (DM) is one of the most investigated and computationally implemented functions. The literature reports several computational models that enable AAs to make decisions that help achieve their personal goals and needs. However, most models disregard crucial aspects of human decision-making such as other agents' needs, ethical values, and social norms. In this paper, the authors present a set of criteria and mechanisms proposed to develop a biologically inspired computational model of Moral Decision-Making (MDM). To achieve a process of moral decision-making believable, the authors propose a cognitive function to determine the importance of each criterion based on the mood and emotional state of AAs, the main objective the model is to enable AAs to make decisions based on ethical and moral judgment.

scholarly journals Incorporating Failure Events in Agents’ Decision Making to Improve User Satisfaction

2020 ◽  
Author(s):  
Chen Rozenshtein ◽  
David Sarne
Keyword(s):  
Decision Making ◽  
User Satisfaction ◽  
Large Scale ◽  
Autonomous Agents ◽  
Human Subjects ◽  
Amazon Mechanical Turk ◽  
Direct Influence ◽  
New Paradigm ◽  
Joint Task ◽  
Satisfaction Measures

This paper suggests a new paradigm for the design of collaborative autonomous agents engaged in executing a joint task alongside a human user. In particular, we focus on the way an agent's failures should affect its decision making, as far as user satisfaction measures are concerned. Unlike the common practice that considers agent (and more broadly, system) failures solely in the prism of their influence over the agent's contribution to the execution of the joint task, we argue that there is an additional, direct, influence which cannot be fully captured by the above measure. Through two series of large-scale controlled experiments with 450 human subjects, recruited through Amazon Mechanical Turk, we show that, indeed, such direct influence holds. Furthermore, we show that the use of a simple agent design that takes into account the direct influence of failures in its decision making yields considerably better user satisfaction, compared to an agent that focuses exclusively on maximizing its absolute contribution to the joint task.

Using Serious Games for Collecting and Modeling Human Procurement Decisions in a Supply Chain Context

2012 ◽  
pp. 135-156
Author(s):  
Souleiman Naciri ◽  
Min-Jung Yoo ◽  
Rémy Glardon
Keyword(s):  
Decision Making ◽  
Computer Simulation ◽  
Supply Chain ◽  
Operations Management ◽  
Simulation Models ◽  
Human Agent ◽  
Human Decision ◽  
Planning Processes ◽  
The Impact ◽  
A Company

Computer simulation is often used for studying specific issues in supply chains or for evaluating the impact of eligible design and calibration solutions on the performance of a company and its supply chain. In computer simulations, production facilities and planning processes are modeled in order to correctly characterize the supply chain behavior. However, very little attention has been given so far in these models to human decisions. Because human decisions are very complex and may vary across individuals or with time, they are largely neglected in traditional simulation models. This restricts the models’ reliability and utility. The first thing that must be done in order to include human decisions in simulation models is to capture how people actually make decisions. This chapter presents a serious game called DecisionTack, which was specifically developed to capture the human decision-making process in operations management (the procurement process). It captures both the information the human agent consults and the decisions he or she makes.

Using Serious Games for Collecting and Modeling Human Procurement Decisions in a Supply Chain Context

2012 ◽  
pp. 744-765
Author(s):  
Souleiman Naciri ◽  
Min-Jung Yoo ◽  
Rémy Glardon
Keyword(s):  
Decision Making ◽  
Computer Simulation ◽  
Supply Chain ◽  
Operations Management ◽  
Simulation Models ◽  
Human Agent ◽  
Human Decision ◽  
Planning Processes ◽  
The Impact ◽  
A Company

Computer simulation is often used for studying specific issues in supply chains or for evaluating the impact of eligible design and calibration solutions on the performance of a company and its supply chain. In computer simulations, production facilities and planning processes are modeled in order to correctly characterize the supply chain behavior. However, very little attention has been given so far in these models to human decisions. Because human decisions are very complex and may vary across individuals or with time, they are largely neglected in traditional simulation models. This restricts the models’ reliability and utility. The first thing that must be done in order to include human decisions in simulation models is to capture how people actually make decisions. This chapter presents a serious game called DecisionTack, which was specifically developed to capture the human decision-making process in operations management (the procurement process). It captures both the information the human agent consults and the decisions he or she makes.

Sign in / Sign up

Export Citation Format

Share Document