Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shapira, Eilam, Madmon, Omer, Apel, Reut, Tennenholtz, Moshe, Reichart, Roi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912671060721664
author Shapira, Eilam
Madmon, Omer
Apel, Reut
Tennenholtz, Moshe
Reichart, Roi
author_facet Shapira, Eilam
Madmon, Omer
Apel, Reut
Tennenholtz, Moshe
Reichart, Roi
contents Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents. This paper addresses a key aspect in the design of such agents: predicting human decisions in off-policy evaluation (OPE). We focus on language-based persuasion games, where an expert aims to influence the decision-maker through verbal messages. In our OPE framework, the prediction model is trained on human interaction data collected from encounters with one set of expert agents, and its performance is evaluated on interactions with a different set of experts. Using a dedicated application, we collected a dataset of 87K decisions from humans playing a repeated decision-making game with artificial agents. To enhance off-policy performance, we propose a simulation technique involving interactions across the entire agent space and simulated decision-makers. Our learning strategy yields significant OPE gains, e.g., improving prediction accuracy in the top 15% challenging cases by 7.1%. Our code and the large dataset we collected and generated are submitted as supplementary material and publicly available in our GitHub repository: https://github.com/eilamshapira/HumanChoicePrediction
format Preprint
id arxiv_https___arxiv_org_abs_2305_10361
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation
Shapira, Eilam
Madmon, Omer
Apel, Reut
Tennenholtz, Moshe
Reichart, Roi
Machine Learning
Artificial Intelligence
Computer Science and Game Theory
Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents. This paper addresses a key aspect in the design of such agents: predicting human decisions in off-policy evaluation (OPE). We focus on language-based persuasion games, where an expert aims to influence the decision-maker through verbal messages. In our OPE framework, the prediction model is trained on human interaction data collected from encounters with one set of expert agents, and its performance is evaluated on interactions with a different set of experts. Using a dedicated application, we collected a dataset of 87K decisions from humans playing a repeated decision-making game with artificial agents. To enhance off-policy performance, we propose a simulation technique involving interactions across the entire agent space and simulated decision-makers. Our learning strategy yields significant OPE gains, e.g., improving prediction accuracy in the top 15% challenging cases by 7.1%. Our code and the large dataset we collected and generated are submitted as supplementary material and publicly available in our GitHub repository: https://github.com/eilamshapira/HumanChoicePrediction
title Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation
topic Machine Learning
Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2305.10361