Advantage Alignment Algorithms

• URL: http://arxiv.org/abs/2406.14662v2
• Date: Thu, 03 Oct 2024 15:52:17 GMT
• Title: Advantage Alignment Algorithms
• Authors: Juan Agustin Duque, Milad Aghajohari, Tim Cooijmans, Razvan Ciuca, Tianyu Zhang, Gauthier Gidel, Aaron Courville,
• Abstract summary: We introduce Advantage Alignment, a family of algorithms that perform opponent shaping efficiently and intuitively. We achieve this by aligning the advantages of interacting agents, increasing the probability of mutually beneficial actions when their interaction has been positive. We demonstrate the effectiveness of our algorithms across a range of social dilemmas, achieving state-of-the-art cooperation and robustness against exploitation.
• Score: 20.125992203908744
• License:
• Abstract: Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts, particularly in general-sum games where naive reinforcement learning agents empirically converge to Pareto-suboptimal Nash equilibria. To address this issue, opponent shaping has emerged as a paradigm for finding socially beneficial equilibria in general-sum games. In this work, we introduce Advantage Alignment, a family of algorithms derived from first principles that perform opponent shaping efficiently and intuitively. We achieve this by aligning the advantages of interacting agents, increasing the probability of mutually beneficial actions when their interaction has been positive. We prove that existing opponent shaping methods implicitly perform Advantage Alignment. Compared to these methods, Advantage Alignment simplifies the mathematical formulation of opponent shaping, reduces the computational burden and extends to continuous action domains. We demonstrate the effectiveness of our algorithms across a range of social dilemmas, achieving state-of-the-art cooperation and robustness against exploitation.

Related papers

• Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents [2.1301560294088318]
  Cooperation between self-interested individuals is a widespread phenomenon in the natural world, but remains elusive in interactions between artificially intelligent agents. We introduce Reciprocators, reinforcement learning agents which are intrinsically motivated to reciprocate the influence of opponents' actions on their returns. We show that Reciprocators can be used to promote cooperation in temporally extended social dilemmas during simultaneous learning.
  arXiv  Detail & Related papers  (2024-06-03T06:07:27Z)
• LOQA: Learning with Opponent Q-Learning Awareness [1.1666234644810896]
  We introduce Learning with Opponent Q-Learning Awareness (LOQA), a decentralized reinforcement learning algorithm tailored to optimize an agent's individual utility. LOQA achieves state-of-the-art performance in benchmark scenarios such as the Iterated Prisoner's Dilemma and the Coin Game.
  arXiv  Detail & Related papers  (2024-05-02T06:33:01Z)
• A Minimaximalist Approach to Reinforcement Learning from Human Feedback [49.45285664482369]
  We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training. We demonstrate that on a suite of continuous control tasks, we are able to learn significantly more efficiently than reward-model based approaches.
  arXiv  Detail & Related papers  (2024-01-08T17:55:02Z)
• Efficiently Computing Nash Equilibria in Adversarial Team Markov Games [19.717850955051837]
  We introduce a class of games in which a team identically players is competing against an adversarial player. This setting allows for a unifying treatment of zero-sum Markov games potential games. Our main contribution is the first algorithm for computing stationary $epsilon$-approximate Nash equilibria in adversarial team Markov games.
  arXiv  Detail & Related papers  (2022-08-03T16:41:01Z)
• Enhancing Adversarial Training with Feature Separability [52.39305978984573]
  We introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to boost the intra-class feature similarity and increase inter-class feature variance. Through comprehensive experiments, we demonstrate that the proposed ATFS framework significantly improves both clean and robust performance.
  arXiv  Detail & Related papers  (2022-05-02T04:04:23Z)
• 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)
• On Information Asymmetry in Competitive Multi-Agent Reinforcement Learning: Convergence and Optimality [78.76529463321374]
  We study the system of interacting non-cooperative two Q-learning agents. We show that this information asymmetry can lead to a stable outcome of population learning.
  arXiv  Detail & Related papers  (2020-10-21T11:19:53Z)
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions [80.49176924360499]
  We establish a framework for directing a society of simple, specialized, self-interested agents to solve sequential decision problems. We derive a class of decentralized reinforcement learning algorithms. We demonstrate the potential advantages of a society's inherent modular structure for more efficient transfer learning.
  arXiv  Detail & Related papers  (2020-07-05T16:41:09Z)
• Cooperative Inverse Reinforcement Learning [64.60722062217417]
  We propose a formal definition of the value alignment problem as cooperative reinforcement learning (CIRL) A CIRL problem is a cooperative, partial-information game with two agents human and robot; both are rewarded according to the human's reward function, but the robot does not initially know what this is. In contrast to classical IRL, where the human is assumed to act optimally in isolation, optimal CIRL solutions produce behaviors such as active teaching, active learning, and communicative actions.
  arXiv  Detail & Related papers  (2016-06-09T22:39:54Z)

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.