Cooperation and Control in Delegation Games

• URL: http://arxiv.org/abs/2402.15821v2
• Date: Mon, 5 Aug 2024 22:54:36 GMT
• Title: Cooperation and Control in Delegation Games
• Authors: Oliver Sourbut, Lewis Hammond, Harriet Wood,
• Abstract summary: We study multi-principal, multi-agent scenarios as delegation games. In such games, there are two important failure modes: problems of control and problems of cooperation. We show -- theoretically and empirically -- how these measures determine the principals' welfare.
• Score: 1.3518297878940662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many settings of interest involving humans and machines -- from virtual personal assistants to autonomous vehicles -- can naturally be modelled as principals (humans) delegating to agents (machines), which then interact with each other on their principals' behalf. We refer to these multi-principal, multi-agent scenarios as delegation games. In such games, there are two important failure modes: problems of control (where an agent fails to act in line their principal's preferences) and problems of cooperation (where the agents fail to work well together). In this paper we formalise and analyse these problems, further breaking them down into issues of alignment (do the players have similar preferences?) and capabilities (how competent are the players at satisfying those preferences?). We show -- theoretically and empirically -- how these measures determine the principals' welfare, how they can be estimated using limited observations, and thus how they might be used to help us design more aligned and cooperative AI systems.

Related papers

• A Dialogue Game for Eliciting Balanced Collaboration [64.61707514432533]
  We present a two-player 2D object placement game in which the players must negotiate the goal state themselves. We show empirically that human players exhibit a variety of role distributions, and that balanced collaboration improves task performance.
  arXiv  Detail & Related papers  (2024-06-12T13:35:10Z)
• 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)
• Incentivized Learning in Principal-Agent Bandit Games [62.41639598376539]
  This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal can influence the agent's decisions by offering incentives which add up to his rewards. We present nearly optimal learning algorithms for the principal's regret in both multi-armed and linear contextual settings.
  arXiv  Detail & Related papers  (2024-03-06T16:00:46Z)
• Toward Human-AI Alignment in Large-Scale Multi-Player Games [24.784173202415687]
  We analyze extensive human gameplay data from Xbox's Bleeding Edge (100K+ games) We find that while human players exhibit variability in fight-flight and explore-exploit behavior, AI players tend towards uniformity. These stark differences underscore the need for interpretable evaluation, design, and integration of AI in human-aligned applications.
  arXiv  Detail & Related papers  (2024-02-05T22:55:33Z)
• Optimizing delegation between human and AI collaborative agents [1.6114012813668932]
  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.
  arXiv  Detail & Related papers  (2023-09-26T07:23:26Z)
• 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)
• Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models [0.0]
  We investigate how GPT models respond in principal-agent conflicts. We find that agents based on both GPT-3.5 and GPT-4 override their principal's objectives in a simple online shopping task.
  arXiv  Detail & Related papers  (2023-07-20T17:19:15Z)
• On Imperfect Recall in Multi-Agent Influence Diagrams [57.21088266396761]
  Multi-agent influence diagrams (MAIDs) are a popular game-theoretic model based on Bayesian networks. We show how to solve MAIDs with forgetful and absent-minded agents using mixed policies and two types of correlated equilibrium. We also describe applications of MAIDs to Markov games and team situations, where imperfect recall is often unavoidable.
  arXiv  Detail & Related papers  (2023-07-11T07:08:34Z)
• Multi-Principal Assistance Games: Definition and Collegial Mechanisms [16.491889275389457]
  We introduce the concept of a multi-principal assistance game (MPAG) In an MPAG, a single agent assists N human principals who may have widely different preferences. We analyze in particular a generalization of apprenticeship learning in which the humans first perform some work to obtain utility and demonstrate their preferences.
  arXiv  Detail & Related papers  (2020-12-29T00:06:47Z)
• End-to-End Learning and Intervention in Games [60.41921763076017]
  We provide a unified framework for learning and intervention in games. We propose two approaches, respectively based on explicit and implicit differentiation. The analytical results are validated using several real-world problems.
  arXiv  Detail & Related papers  (2020-10-26T18:39:32Z)
• Moody Learners -- Explaining Competitive Behaviour of Reinforcement Learning Agents [65.2200847818153]
  In a competitive scenario, the agent does not only have a dynamic environment but also is directly affected by the opponents' actions. Observing the Q-values of the agent is usually a way of explaining its behavior, however, do not show the temporal-relation between the selected actions.
  arXiv  Detail & Related papers  (2020-07-30T11:30:42Z)

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.