Optimizing delegation between human and AI collaborative agents
- URL: http://arxiv.org/abs/2309.14718v2
- Date: Wed, 11 Oct 2023 07:28:04 GMT
- Title: Optimizing delegation between human and AI collaborative agents
- Authors: Andrew Fuchs, Andrea Passarella, Marco Conti
- Abstract summary: We train a delegating manager agent to make delegation decisions with respect to potential performance deficiencies.
Our framework learns through observations of team performance without restricting agents to matching dynamics.
Our results show our manager learns to perform delegation decisions with teams of agents operating under differing representations of the environment.
- Score: 1.6114012813668932
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In the context of humans operating with artificial or autonomous agents in a
hybrid team, it is essential to accurately identify when to authorize those
team members to perform actions. Given past examples where humans and
autonomous systems can either succeed or fail at tasks, we seek to train a
delegating manager agent to make delegation decisions with respect to these
potential performance deficiencies. Additionally, we cannot always expect the
various agents to operate within the same underlying model of the environment.
It is possible to encounter cases where the actions and transitions would vary
between agents. Therefore, our framework provides a manager model which learns
through observations of team performance without restricting agents to matching
dynamics. Our results show our manager learns to perform delegation decisions
with teams of agents operating under differing representations of the
environment, significantly outperforming alternative methods to manage the
team.
Related papers
- Optimizing Risk-averse Human-AI Hybrid Teams [1.433758865948252]
We propose a manager which learns, through a standard Reinforcement Learning scheme, how to best delegate.
We demonstrate the optimality of our manager's performance in several grid environments.
Our results show our manager can successfully learn desirable delegations which result in team paths near/exactly optimal.
arXiv Detail & Related papers (2024-03-13T09:49:26Z) - Optimizing Delegation in Collaborative Human-AI Hybrid Teams [1.433758865948252]
We address the case of hybrid teams in which only one team member (the control agent) is authorized to act as control for the team.
We propose the addition of an AI manager which learns as an outside observer of the team.
We demonstrate our manager performance in a simulated driving scenario representing the case of a hybrid team of agents composed of a human driver and autonomous driving system.
arXiv Detail & Related papers (2024-02-08T12:04:43Z) - AgentCF: Collaborative Learning with Autonomous Language Agents for
Recommender Systems [112.76941157194544]
We propose AgentCF for simulating user-item interactions in recommender systems through agent-based collaborative filtering.
We creatively consider not only users but also items as agents, and develop a collaborative learning approach that optimize both kinds of agents together.
Overall, the optimized agents exhibit diverse interaction behaviors within our framework, including user-item, user-user, item-item, and collective interactions.
arXiv Detail & Related papers (2023-10-13T16:37:14Z) - ProAgent: Building Proactive Cooperative Agents with Large Language
Models [89.53040828210945]
ProAgent is a novel framework that harnesses large language models to create proactive agents.
ProAgent can analyze the present state, and infer the intentions of teammates from observations.
ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
arXiv Detail & Related papers (2023-08-22T10:36:56Z) - AgentVerse: Facilitating Multi-Agent Collaboration and Exploring
Emergent Behaviors [93.38830440346783]
We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system.
Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent.
In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
arXiv Detail & Related papers (2023-08-21T16:47:11Z) - Compensating for Sensing Failures via Delegation in Human-AI Hybrid
Systems [0.0]
We consider the hybrid human-AI teaming case where a managing agent is tasked with identifying when to perform a delegation assignment.
We model how the environmental context can contribute to, or exacerbate, the sensing deficiencies.
We demonstrate how a Reinforcement Learning (RL) manager can correct the context-delegation association.
arXiv Detail & Related papers (2023-03-02T14:27:01Z) - Task Allocation with Load Management in Multi-Agent Teams [4.844411739015927]
We present a decision-making framework for multi-agent teams to learn task allocation with the consideration of load management.
We illustrate the effect of load management on team performance and explore agent behaviors in example scenarios.
A measure of agent importance in collaboration is developed to infer team resilience when facing potential overload situations.
arXiv Detail & Related papers (2022-07-17T20:17:09Z) - LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent
Reinforcement Learning [122.47938710284784]
We propose a novel framework for learning dynamic subtask assignment (LDSA) in cooperative MARL.
To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy.
We show that LDSA learns reasonable and effective subtask assignment for better collaboration.
arXiv Detail & Related papers (2022-05-05T10:46:16Z) - Learning Latent Representations to Influence Multi-Agent Interaction [65.44092264843538]
We propose a reinforcement learning-based framework for learning latent representations of an agent's policy.
We show that our approach outperforms the alternatives and learns to influence the other agent.
arXiv Detail & Related papers (2020-11-12T19:04:26Z) - Too many cooks: Bayesian inference for coordinating multi-agent
collaboration [55.330547895131986]
Collaboration requires agents to coordinate their behavior on the fly.
Underlying the human ability to collaborate is theory-of-mind, the ability to infer the hidden mental states that drive others to act.
We develop Bayesian Delegation, a decentralized multi-agent learning mechanism with these abilities.
arXiv Detail & Related papers (2020-03-26T07:43:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.