English
Related papers

Related papers: Stable Opponent Shaping in Differentiable Games

200 papers

Learning in general-sum games is unstable and frequently leads to socially undesirable (Pareto-dominated) outcomes. To mitigate this, Learning with Opponent-Learning Awareness (LOLA) introduced opponent shaping to this setting, by…

Machine Learning · Computer Science 2022-06-28 Timon Willi , Alistair Letcher , Johannes Treutlein , Jakob Foerster

Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and…

Artificial Intelligence · Computer Science 2018-09-21 Jakob N. Foerster , Richard Y. Chen , Maruan Al-Shedivat , Shimon Whiteson , Pieter Abbeel , Igor Mordatch

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often…

Machine Learning · Computer Science 2022-10-20 Stephen Zhao , Chris Lu , Roger Baker Grosse , Jakob Nicolaus Foerster

We consider a scenario in which two reinforcement learning agents repeatedly play a matrix game against each other and update their parameters after each round. The agents' decision-making is transparent to each other, which allows each…

Artificial Intelligence · Computer Science 2021-08-23 Adrian Hutter

Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment…

Machine Learning · Computer Science 2020-06-09 Ian Davies , Zheng Tian , Jun Wang

Reinforcement learning solutions have great success in the 2-player general sum setting. In this setting, the paradigm of Opponent Shaping (OS), in which agents account for the learning of their co-players, has led to agents which are able…

Machine Learning · Computer Science 2023-12-27 Alexandra Souly , Timon Willi , Akbir Khan , Robert Kirk , Chris Lu , Edward Grefenstette , Tim Rocktäschel

In general-sum games, the interaction of self-interested learning agents commonly leads to collectively worst-case outcomes, such as defect-defect in the iterated prisoner's dilemma (IPD). To overcome this, some methods, such as Learning…

Artificial Intelligence · Computer Science 2022-11-07 Chris Lu , Timon Willi , Christian Schroeder de Witt , Jakob Foerster

Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strategy that aims to maximize its own reward may fall into a local optimum.…

Artificial Intelligence · Computer Science 2026-02-02 Xinyu Qiao , Yudong Hu , Congying Han , Weiyan Wu , Tiande Guo

Large Language Models (LLMs) are increasingly being deployed as autonomous agents in real-world environments. As these deployments scale, multi-agent interactions become inevitable, making it essential to understand strategic behavior in…

Machine Learning · Computer Science 2025-10-10 Marta Emili Garcia Segura , Stephen Hailes , Mirco Musolesi

Human coordination often relies on the ability to influence the beliefs of others through strategic action. In multi-agent reinforcement learning, opponent shaping attempts to replicate this influence, though existing methods typically…

Artificial Intelligence · Computer Science 2026-05-29 Aarav G Sane , Karthik Sivachandran , Rohan Paleja

We propose Searching with Opponent-Awareness (SOA), an approach to leverage opponent-aware planning without explicit or a priori opponent models for improving performance and social welfare in multi-agent systems. To this end, we develop an…

Multiagent Systems · Computer Science 2021-04-22 Timy Phan

We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooperation. LOLA and POLA agents learn reciprocity-based…

Computer Science and Game Theory · Computer Science 2024-04-11 Milad Aghajohari , Tim Cooijmans , Juan Agustin Duque , Shunichi Akatsuka , Aaron Courville

Learning anticipation is a reasoning paradigm in multi-agent reinforcement learning, where agents, during learning, consider the anticipated learning of other agents. There has been substantial research into the role of learning…

Multiagent Systems · Computer Science 2023-04-04 Ariyan Bighashdel , Daan de Geus , Pavol Jancura , Gijs Dubbelman

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is…

The universe involves many independent co-learning agents as an ever-evolving part of our observed environment. Yet, in practice, Multi-Agent Reinforcement Learning (MARL) applications are typically constrained to small, homogeneous…

Machine Learning · Computer Science 2025-04-29 Yann Bouteiller , Karthik Soma , Giovanni Beltrame

In multi-agent settings with mixed incentives, methods developed for zero-sum games have been shown to lead to detrimental outcomes. To address this issue, opponent shaping (OS) methods explicitly learn to influence the learning dynamics of…

Artificial Intelligence · Computer Science 2024-02-13 Akbir Khan , Timon Willi , Newton Kwan , Andrea Tacchetti , Chris Lu , Edward Grefenstette , Tim Rocktäschel , Jakob Foerster

In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiquitous relevance of such settings, decentralized machine…

Computer Science and Game Theory · Computer Science 2024-05-03 Milad Aghajohari , Juan Agustin Duque , Tim Cooijmans , Aaron Courville

Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and game-theoretic environments. Existing approaches often entangle opponent modeling with…

Artificial Intelligence · Computer Science 2026-05-11 Shiyue Cao , Pei Xu , Likun Yang , Lei Cui , Xiaotang Chen , Kaiqi Huang

We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We seek to design strategies for the learner to successfully interact with the opponent. While most previous…

Machine Learning · Computer Science 2020-07-13 Pier Giuseppe Sessa , Ilija Bogunovic , Maryam Kamgarpour , Andreas Krause

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. Recently, there are robust learning methods aiming at this…

Machine Learning · Computer Science 2021-05-12 Jiashuo Liu , Zheyan Shen , Peng Cui , Linjun Zhou , Kun Kuang , Bo Li , Yishi Lin
‹ Prev 1 2 3 10 Next ›