Human-Agent Coordination in Games under Incomplete Information via Multi-Step Intent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Shenghui, Zhao, Ruihan, Chinchali, Sandeep, Topcu, Ufuk
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916618723917824
author Chen, Shenghui
Zhao, Ruihan
Chinchali, Sandeep
Topcu, Ufuk
author_facet Chen, Shenghui
Zhao, Ruihan
Chinchali, Sandeep
Topcu, Ufuk
contents Strategic coordination between autonomous agents and human partners under incomplete information can be modeled as turn-based cooperative games. We extend a turn-based game under incomplete information, the shared-control game, to allow players to take multiple actions per turn rather than a single action. The extension enables the use of multi-step intent, which we hypothesize will improve performance in long-horizon tasks. To synthesize cooperative policies for the agent in this extended game, we propose an approach featuring a memory module for a running probabilistic belief of the environment dynamics and an online planning algorithm called IntentMCTS. This algorithm strategically selects the next action by leveraging any communicated multi-step intent via reward augmentation while considering the current belief. Agent-to-agent simulations in the Gnomes at Night testbed demonstrate that IntentMCTS requires fewer steps and control switches than baseline methods. A human-agent user study corroborates these findings, showing an 18.52% higher success rate compared to the heuristic baseline and a 5.56% improvement over the single-step prior work. Participants also report lower cognitive load, frustration, and higher satisfaction with the IntentMCTS agent partner.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18242
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Human-Agent Coordination in Games under Incomplete Information via Multi-Step Intent
Chen, Shenghui
Zhao, Ruihan
Chinchali, Sandeep
Topcu, Ufuk
Artificial Intelligence
Human-Computer Interaction
Strategic coordination between autonomous agents and human partners under incomplete information can be modeled as turn-based cooperative games. We extend a turn-based game under incomplete information, the shared-control game, to allow players to take multiple actions per turn rather than a single action. The extension enables the use of multi-step intent, which we hypothesize will improve performance in long-horizon tasks. To synthesize cooperative policies for the agent in this extended game, we propose an approach featuring a memory module for a running probabilistic belief of the environment dynamics and an online planning algorithm called IntentMCTS. This algorithm strategically selects the next action by leveraging any communicated multi-step intent via reward augmentation while considering the current belief. Agent-to-agent simulations in the Gnomes at Night testbed demonstrate that IntentMCTS requires fewer steps and control switches than baseline methods. A human-agent user study corroborates these findings, showing an 18.52% higher success rate compared to the heuristic baseline and a 5.56% improvement over the single-step prior work. Participants also report lower cognitive load, frustration, and higher satisfaction with the IntentMCTS agent partner.
title Human-Agent Coordination in Games under Incomplete Information via Multi-Step Intent
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2410.18242