Related papers: On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents

On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents

URL: http://arxiv.org/abs/2407.00419v1
Date: Sat, 29 Jun 2024 11:59:52 GMT
Title: On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents
Authors: Robert Loftin, Saptarashmi Bandyopadhyay, Mustafa Mert Çelikok,
Abstract summary: We consider the problem of cooperating with a textitpopulation of agents in a finitely-repeated, two player general-sum matrix game with private utilities. Our results first show that these assumptions alone are insufficient to ensure textitzero-shot cooperation with members of the target population. We provide upper and lower bounds on the number of samples needed to learn an effective cooperation strategy.
Score: 17.015143707851358
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Artificially intelligent agents deployed in the real-world will require the ability to reliably \textit{cooperate} with humans (as well as other, heterogeneous AI agents). To provide formal guarantees of successful cooperation, we must make some assumptions about how partner agents could plausibly behave. Any realistic set of assumptions must account for the fact that other agents may be just as adaptable as our agent is. In this work, we consider the problem of cooperating with a \textit{population} of agents in a finitely-repeated, two player general-sum matrix game with private utilities. Two natural assumptions in such settings are that: 1) all agents in the population are individually rational learners, and 2) when any two members of the population are paired together, with high-probability they will achieve at least the same utility as they would under some Pareto efficient equilibrium strategy. Our results first show that these assumptions alone are insufficient to ensure \textit{zero-shot} cooperation with members of the target population. We therefore consider the problem of \textit{learning} a strategy for cooperating with such a population using prior observations its members interacting with one another. We provide upper and lower bounds on the number of samples needed to learn an effective cooperation strategy. Most importantly, we show that these bounds can be much stronger than those arising from a "naive'' reduction of the problem to one of imitation learning.

Related papers

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation [64.27636858152522]
Decentralized agents must cooperate given only partial egocentric views of the world. We train generative models to estimate the overall world state given partial egocentric observations. We learn a compositional world model for multi-agent cooperation by factorizing the naturally composable joint actions of multiple agents.
arXiv Detail & Related papers (2024-04-16T17:59:11Z)
An Extensible Framework for Open Heterogeneous Collaborative Perception [58.70875361688463]
Collaborative perception aims to mitigate the limitations of single-agent perception. In this paper, we introduce a new open heterogeneous problem: how to accommodate continually emerging new heterogeneous agent types into collaborative perception. We propose HEterogeneous ALliance (HEAL), a novel collaborative perception framework.
arXiv Detail & Related papers (2024-01-25T05:55:03Z)
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)
Towards a Unifying Model of Rationality in Multiagent Systems [11.321217099465196]
Multiagent systems need to cooperate with other agents (including humans) nearly as effectively as these agents cooperate with one another. We propose a generic model of socially intelligent agents, which are individually rational learners that are also able to cooperate with one another. We show how we can construct socially intelligent agents for different forms of regret.
arXiv Detail & Related papers (2023-05-29T13:18:43Z)
PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination [52.991211077362586]
We propose a policy ensemble method to increase the diversity of partners in the population. We then develop a context-aware method enabling the ego agent to analyze and identify the partner's potential policy primitives. In this way, the ego agent is able to learn more universal cooperative behaviors for collaborating with diverse partners.
arXiv Detail & Related papers (2023-01-16T12:14:58Z)
Similarity-based cooperative equilibrium [29.779551971013074]
In social dilemmas like the one-shot Prisoner's Dilemma, standard game theory predicts that ML agents will fail to cooperate with each other. We introduce a more realistic setting in which agents only observe a single number indicating how similar they are to each other. We prove that this allows for the same set of cooperative outcomes as the full transparency setting.
arXiv Detail & Related papers (2022-11-26T03:43:13Z)
The art of compensation: how hybrid teams solve collective risk dilemmas [6.081979963786028]
We study the evolutionary dynamics of cooperation in a hybrid population made of both adaptive and fixed-behavior agents. We show how the first learn to adapt their behavior to compensate for the behavior of the latter.
arXiv Detail & Related papers (2022-05-13T13:23:42Z)
Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning [4.060731229044571]
Ad hoc teamwork problem describes situations where an agent has to cooperate with previously unseen agents to achieve a common goal. One could implement cooperative skills into an agent by using domain knowledge to design the agent's behavior. We apply meta-reinforcement learning (meta-RL) formulation in the context of the ad hoc teamwork problem.
arXiv Detail & Related papers (2021-11-05T12:01:28Z)
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning [53.73686229912562]
We propose a novel MARL approach called Universal Value Exploration (UneVEn) UneVEn learns a set of related tasks simultaneously with a linear decomposition of universal successor features. Empirical results on a set of exploration games, challenging cooperative predator-prey tasks requiring significant coordination among agents, and StarCraft II micromanagement benchmarks show that UneVEn can solve tasks where other state-of-the-art MARL methods fail.
arXiv Detail & Related papers (2020-10-06T19:08:47Z)
Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams [0.0]
We develop a competitive multi agent environment called FortAttack in which two teams compete against each other. We observe a natural emergence of heterogeneous behavior amongst homogeneous agents when such behavior can lead to the team's success. We propose ensemble training, in which we utilize the evolved opponent strategies to train a single policy for friendly agents.
arXiv Detail & Related papers (2020-07-06T22:35:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.