The Life Game: Cognitive Strategies for Repeated Stochastic Games

Cheng, Kan-Leung; Zuckerman, Inon; Nau, Dana S.; Golbeck, Jennifer

doi:10.1109/passat/socialcom.2011.62

Cited by 12 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the explanations given for the difference between the two methods is people's tendency to be influenced by emotions, whereas in the strategy method people are in a "cold" state and are less emotionally aroused [34]. The main difference between the strategy method and the PDA technology is that, in the first, participants need to describe their choices for each possible state, whereas with PDAs the requirement is to express a cohesive formulation of their strategy [2,5,37]. This entails various implications related to the time it takes to capture one's strategy (an advantage for the PDAs in cases where the possible number of system's states is large and an advantage for the strategy method when the game is extremely simple, e.g., in the ultimatum game), the ability to understand one's strategy (an advantage for PDAs, as their code can be analyzed afterwards) and the ability to use the strategy when the setting slightly changes (impossible with the strategy method).…”

Section: Related Workmentioning

confidence: 99%

“…Examples of such discrepancies include over-reporting of political participation [39] and contrasting results between self-reported and performance-based levels of physical limitations [40]. Yet, much of the PDA literature tends to assume that people can successfully (to some extent) capture their real-life strategy in a given domain when programming an agent [2,37]. Even in cases where some discrepancy between PDAs and people's behavior is reported, the average performance is reported to be similar, suggesting that PDAs can replace people in mechanism evaluation [1,4].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Agent development as a strategy shaper

Elmalech

Sarne

Agmon

2015

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

This paper studies to what extent agent development changes one's own strategy. While this question has many general implications it is of special interest to the study of peer designed agents (PDAs), which are computer agents developed by non-experts. This latter emerging technology, has been widely advocated in recent literature for the purpose of replacing people in simulations and investigating human behavior. Its main premise is that strategies programmed into these agents reliably reflect, to some extent, the behavior used by their programmers in real life. We show that PDA development has an important side effect that has not been addressed to date-the process that merely attempts to capture one's strategy is also likely to affect the developer's strategy. This result has many implications concerning the appropriate design of PDA-based simulations as well as the validity of using PDAs for studying individual decision making. The phenomenon is demonstrated experimentally, using two very different application domains and several performance measures. Our findings suggest that the effects on one's strategy arise both in situations where it is potentially possible for people to reason about the optimal strategy (in which case PDA development will enhance the use of an optimal strategy) and in those where calculating the optimal strategy is computationally challenging (in which case PDA development will push people to use more effective strategies, on average). Since in our experiments PDA development actually improved the developer's strategy, PDA development can be suggested as a means for improving people's problem solving skills. Finally, we show that the improvement achieved in people's strategies through agent development is not attributed to the expressive aspect of agent development per-se but rather there is a crucial additional gain in the process of designing and programming ones strategy into an agent.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Agent development as a strategy shaper

Elmalech

Sarne

Agmon

2015

Auton Agent Multi-Agent Syst

View full text Add to dashboard Cite

show abstract

“…One of the explanations given for the difference between the two methods is the tendency of people to be influenced by emotions, where in strategy method people are in a "cold" state and are less emotionally arouse [10]. The main difference between the strategy method and PDAs technology is that in the first participants need to enumerate their choices for each possible state of the game, whereas with PDAs the requirement is to express a cohesive formulation of their strategy [12,14,44]. This entails various implications related to the time it takes to capture one's strategy (an advantage for the PDAs in cases where the possible system's state is large and an advantage for the strategy method when the game is extremely simple, e.g., in the ultimatum game), the ability to understand one's strategy (an advantage for PDAs, as their code can be analyzed afterwards) and the ability to use the strategy when the setting slightly changes (impossible with the strategy method).…”

Section: Related Workmentioning

confidence: 99%

“…Indeed, part of the PDA-based literature simply does not consider the PDAs-people similarity question as an issue or attempt to make any claims regarding this aspect (e.g., in TAC [25,48,63]). Yet, much of the PDA literature tends to assume that people can successfully (to some extent) capture their real-life strategy in a given domain when programming an agent [14,44]. Even in cases where some discrepancy between PDAs and people's behavior is reported, the average performance is reported to be similar, suggesting that PDAs can replace people in mechanism evaluation [30,31].…”

Section: Related Workmentioning

confidence: 99%

Evaluating the applicability of peer-designed agents for mechanism evaluation

Elmalech

Sarne

2014

Web Intelligence and Agent Systems: An International Journal

View full text Add to dashboard Cite

In this paper we empirically investigate the feasibility of using peer-designed agents (PDAs) instead of people for the purpose of mechanism evaluation. This approach has been increasingly advocated in agent research in recent years, mainly due to its many benefits in terms of time and cost. Our experiments compare the behavior of 31 PDAs and 150 people in a legacy eCommerce-based price-exploration setting, using different price-setting mechanisms and diverse performance measures. The results show a varying level of similarity between the aggregate behavior obtained when using people and when using PDAs. In some settings similar results were obtained, in others the use of PDAs rather than people yielded substantial differences. This suggests that the ability to generalize results from one successful implementation of PDA-based systems to another, regarding the use of PDAs as a substitute for people in system evaluations, is quite limited. The decision to prefer PDAs for mechanism evaluation is therefore setting dependent and the applicability of the approach must be re-evaluated when switching to a new setting or using a different measure. Furthermore, we show that even in settings where the aggregate behavior is found to be similar, the individual strategies used by agents in each group highly vary. Finally, we report the results of an extensive comparative analysis of the level of optimality reflected in people's and PDAs' individual decisions in our decision making setting. The results show that the decisions of both groups are far from optimal, however the use of PDAs results in strategies that are more than twice as close to the optimal ones.

show abstract

“…Within the field of economics and psychology, validly encapsulating human decision-making is critical for predicting the short and long term effects of a given policy (Neumann & Morgenstern, 1944;Selten, 1998;Kahneman & Tversky, 1979). To computer scientists, accurately predicting people's actions is critical for mixed human-computer systems such as entertainment domains (Maes, 1995), Interactive Tutoring Systems (Murakami, Sugimoto, & Ishida, 2005), adversarial interactions (Cheng, Zuckerman, Nau, & Golbeck, 2011) and mixed human-agent trading environments (Manisterski et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

Combining psychological models with machine learning to better predict people’s decisions

et al. 2012

Self Cite

View full text Add to dashboard Cite

Creating agents that proficiently interact with people is critical for many applications. Towards creating these agents, models are needed that effectively predict people's decisions in a variety of problems. To date, two approaches have been suggested to generally describe people's decision behavior. One approach creates a-priori predictions about people's behavior, either based on theoretical rational behavior or based on psychological models, including bounded rationality. A second type of approach focuses on creating models based exclusively on observations of people's behavior. At the forefront of these types of methods are various machine learning algorithms. This paper explores how these two approaches can be compared and combined in different types of domains. In relatively simple domains, both psychological models and machine learning yield clear prediction models with nearly identical results. In more complex domains, the exact action predicted by psychological models is not even clear, and machine learning models are even less accurate. Nonetheless, we present a novel approach of creating hybrid methods that incorporate features from psychological models in conjunction with machine learning in order to create significantly improved models for predicting people's decisions. To demonstrate these claims, we present an overview of previous and new results, taken from representative domains ranging from a relatively simple optimization problem and complex domains such as negotiation and coordination without communication.

show abstract

The Life Game: Cognitive Strategies for Repeated Stochastic Games

Cited by 12 publications

References 11 publications

Agent development as a strategy shaper

Agent development as a strategy shaper

Evaluating the applicability of peer-designed agents for mechanism evaluation

Combining psychological models with machine learning to better predict people’s decisions

Contact Info

Product

Resources

About