Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

• URL: http://arxiv.org/abs/2208.08798v1
• Date: Thu, 18 Aug 2022 12:33:09 GMT
• Title: Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members
• Authors: Daphne Cornelisse, Thomas Rood, Mateusz Malinowski, Yoram Bachrach, and Tal Kachman
• Abstract summary: We show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks. Our approach creates models that can generalize to games far from the training distribution. An important application of our framework is Explainable AI.
• Score: 13.643650155415484
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of agents and allocating them shares of the reward that promote long-lasting cooperation are difficult tasks. Cooperative game theory offers solution concepts identifying distribution schemes, such as the Shapley value, that fairly reflect the contribution of individuals to the performance of the team or the Core, which reduces the incentive of agents to abandon their team. Applications of such methods include identifying influential features and sharing the costs of joint ventures or team formation. Unfortunately, using these solutions requires tackling a computational barrier as they are hard to compute, even in restricted settings. In this work, we show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks to propose fair and stable payoff allocations. We show that our approach creates models that can generalize to games far from the training distribution and can predict solutions for more players than observed during training. An important application of our framework is Explainable AI: our approach can be used to speed-up Shapley value computations on many instances.

Related papers

• TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition [61.91764883512776]
  We introduce an innovative PEFT method, TeamLoRA, consisting of a collaboration and competition module for experts. By doing so, TeamLoRA connects the experts as a "Team" with internal collaboration and competition, enabling a faster and more accurate PEFT paradigm for multi-task learning.
  arXiv  Detail & Related papers  (2024-08-19T09:58:53Z)
• Cooperation Dynamics in Multi-Agent Systems: Exploring Game-Theoretic Scenarios with Mean-Field Equilibria [0.0]
  This paper investigates strategies to invoke cooperation in game-theoretic scenarios, namely the Iterated Prisoner's Dilemma. Existing cooperative strategies are analyzed for their effectiveness in promoting group-oriented behavior in repeated games. The study extends to scenarios with exponentially growing agent populations.
  arXiv  Detail & Related papers  (2023-09-28T08:57:01Z)
• Multi-Agent Neural Rewriter for Vehicle Routing with Limited Disclosure of Costs [65.23158435596518]
  Solving the multi-vehicle routing problem as a team Markov game with partially observable costs. Our multi-agent reinforcement learning approach, the so-called multi-agent Neural Rewriter, builds on the single-agent Neural Rewriter to solve the problem by iteratively rewriting solutions.
  arXiv  Detail & Related papers  (2022-06-13T09:17:40Z)
• Offsetting Unequal Competition through RL-assisted Incentive Schemes [18.57907480363166]
  This paper investigates the dynamics of competition among organizations with unequal expertise. We design Touch-Mark, a game based on well-known multi-agent-particle-environment.
  arXiv  Detail & Related papers  (2022-01-05T04:47:22Z)
• Secure Distributed Training at Scale [65.7538150168154]
  Training in presence of peers requires specialized distributed training algorithms with Byzantine tolerance. We propose a novel protocol for secure (Byzantine-tolerant) decentralized training that emphasizes communication efficiency.
  arXiv  Detail & Related papers  (2021-06-21T17:00:42Z)
• Distributed Deep Learning in Open Collaborations [49.240611132653456]
  We propose a novel algorithmic framework designed specifically for collaborative training. We demonstrate the effectiveness of our approach for SwAV and ALBERT pretraining in realistic conditions and achieve performance comparable to traditional setups at a fraction of the cost.
  arXiv  Detail & Related papers  (2021-06-18T16:23:13Z)
• Faster Algorithms for Optimal Ex-Ante Coordinated Collusive Strategies in Extensive-Form Zero-Sum Games [123.76716667704625]
  We focus on the problem of finding an optimal strategy for a team of two players that faces an opponent in an imperfect-information zero-sum extensive-form game. In that setting, it is known that the best the team can do is sample a profile of potentially randomized strategies (one per player) from a joint (a.k.a. correlated) probability distribution at the beginning of the game. We provide an algorithm that computes such an optimal distribution by only using profiles where only one of the team members gets to randomize in each profile.
  arXiv  Detail & Related papers  (2020-09-21T17:51:57Z)
• Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning [11.480994804659908]
  We build on graph neural networks to learn agent models and joint-action value models under varying team compositions. We empirically demonstrate that our approach successfully models the effects other agents have on the learner, leading to policies that robustly adapt to dynamic team compositions.
  arXiv  Detail & Related papers  (2020-06-18T10:39:41Z)
• Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions [103.3630903577951]
  We use cooperative game theory to study teams of artificial RL agents as well as real world teams from professional sports. We introduce a parametric model called cooperative game abstractions (CGAs) for estimating CFs from data. We provide identification results and sample bounds complexity for CGA models as well as error bounds in the estimation of the Shapley Value using CGAs.
  arXiv  Detail & Related papers  (2020-06-16T22:03:36Z)
• A Stochastic Team Formation Approach for Collaborative Mobile Crowdsourcing [1.4209473797379666]
  We develop an algorithm that exploit workers knowledge about their SN neighbors and asks a designated leader to recruit a suitable team. The proposed algorithm is inspired from the optimal stopping strategies and uses the odds-algorithm to compute its output. Experimental results show that, compared to the benchmark exponential optimal solution, the proposed approach reduces time and produces reasonable performance results.
  arXiv  Detail & Related papers  (2020-04-28T22:44:37Z)

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.