Learning in One-Shot Strategic Form Games

Altman, Alon; Bercovici-Boden, Avivit; Tennenholtz, Moshe

doi:10.1007/11871842_6

Cited by 19 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work successfully employed Machine Learning (ML) techniques in service of action prediction in an ensemble of games. The first work we are aware of to use ML techniques for action prediction in one-shot strategic-form games is Altman, Bercovici-Boden, and Tennenholtz (2006). This work focuses on the learning of the choices made by individuals in a given game, based on population behavior in the game ensemble and the choices of the particular individual of interest in the other games.…”

Section: Action Prediction In Machine Learningmentioning

confidence: 99%

Predicting Decisions in Language Based Persuasion Games

Apel¹,

Erev²,

Reichart³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Sender-receiver interactions, and specifically persuasion games, are widely researched in economic modeling and artificial intelligence, and serve as a solid foundation for powerful applications. However, in the classic persuasion games setting, the messages sent from the expert to the decision-maker are abstract or well-structured application-specific signals rather than natural (human) language messages, although natural language is a very common communication signal in real-world persuasion setups. This paper addresses the use of natural language in persuasion games, exploring its impact on the decisions made by the players and aiming to construct effective models for the prediction of these decisions.For this purpose, we conduct an online repeated interaction experiment. At each trial of the interaction, an informed expert aims to sell an uninformed decision-maker a vacation in a hotel, by sending her a review that describes the hotel. While the expert is exposed to several scored reviews, the decision-maker observes only the single review sent by the expert, and her payoff in case she chooses to take the hotel is a random draw from the review score distribution available to the expert only. The expert's payoff, in turn, depends on the number of times the decision-maker chooses the hotel.We consider a number of modeling approaches for this setup, differing from each other in the model type (deep neural network (DNN) vs. linear classifier), the type of features used by the model (textual, behavioral or both) and the source of the textual features (DNN-based vs. hand-crafted). Our results demonstrate that given a prefix of the interaction sequence, our models can predict the future decisions of the decision-maker, particularly when a sequential modeling approach and hand-crafted textual features are applied. 1

show abstract

Section: Action Prediction In Machine Learningmentioning

confidence: 99%

Predicting Decisions in Language Based Persuasion Games

Apel¹,

Erev²,

Reichart³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…An alternative model for the results of the current experiments involves the postulated effect of the similarity of payoffs on behavioral consistency (Altman, Bercovici‐Boden, & Tennenholtz, 2006; Michalski, Carbonell, & Mitchell, 1986). For example, the gambles in Table 1 are highly similar across the gain and loss domains: They use the same payoff magnitudes and are differentiated only by their payoff sign.…”

Section: Quantitative Summarymentioning

confidence: 99%

Risk Attitude in Decision Making: In Search of Trait‐Like Constructs

Yechiam

Ert

2011

Topics in Cognitive Science

View full text Add to dashboard Cite

We evaluate the consistency of different constructs affecting risk attitude in individuals' decisions across different levels of risk. Specifically, we contrast views suggesting that risk attitude is a single primitive construct with those suggesting it consists of multiple latent components. Additionally, we evaluate such constructs as sensitivity to losses, diminishing sensitivity to increases in payoff, sensitivity to variance, and risk acceptance (the willingness to accept probable outcomes over certainty). In search of trait-like constructs, the paper reviews experimental results focusing on the consistency of these constructs in different tasks as well as their temporal consistency. Overall, the findings show that the most consistent factor is risk acceptance, and they also demonstrate its potential boundaries. These results are modeled with a simple quantitative index of subjective risk. A survey of decisions under risk further reveals that participants exhibit almost no consistency across different tasks in this setting, highlighting the advantage of experiential tasks for studying individual differences.

show abstract

“…Human Decision Making Predictions Previous work used machine learning to predict human decisions based on non-textual information (Altman et al, 2006;Hartford et al, 2016;Plonsky et al, 2017), as well as textual signals, e.g., for judicial decisions (Aletras et al, 2016;Zhong et al, 2018;Medvedeva et al, 2020;Yang et al, 2019b) and decisions of leading figures (Bak and Oh, 2018). These works formulate the problem as a classification task where the classifier is based on textual (and potentially also other) signals.…”

Section: Related Workmentioning

confidence: 99%

Designing an Automatic Agent for Repeated Language based Persuasion Games

Raifer¹,

Rotman²,

Apel³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Persuasion games are fundamental in economics and AI research and serve as the basis for important applications. However, work on this setup assumes communication with stylized messages that do not consist of rich human language. In this paper we consider a repeated sender (expert) -receiver (decision maker) game, where the sender is fully informed about the state of the world and aims to persuade the receiver to accept a deal by sending one of several possible natural language reviews. We design an automatic expert that plays this repeated game, aiming to achieve the maximal payoff. Our expert is implemented within the Monte Carlo Tree Search (MCTS) algorithm, with deep learning models that exploit behavioral and linguistic signals in order to predict the next action of the decision maker, and the future payoff of the expert given the state of the game and a candidate review. We demonstrate the superiority of our expert over strong baselines, its adaptability to different decision makers, and that its selected reviews are nicely adapted to the proposed deal.

show abstract

Learning in One-Shot Strategic Form Games

Cited by 19 publications

References 12 publications

Predicting Decisions in Language Based Persuasion Games

Predicting Decisions in Language Based Persuasion Games

Risk Attitude in Decision Making: In Search of Trait‐Like Constructs

Designing an Automatic Agent for Repeated Language based Persuasion Games

Contact Info

Product

Resources

About