arXiv:2607. 01498v1 Announce Type: new Abstract: We investigate the problem of learning useful policy representations (embeddings) in two-player zero-sum imperfect-information games.
By Kevin Wang, Kevin Yang, Arjun Prakash, Amy Greenwald
arXiv:2605. 29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss.
By Christoph Dann, Yishay Mansour, Mehryar Mohri
arXiv:2603. 25464v2 Announce Type: replace-cross Abstract: Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward-free dataset, and recover optimal policies for any reward function directly at test time.
By Jiajun Hu, Nuria Armengol Urpi, Jin Cheng, Stelian Coros
arXiv:2607. 06514v1 Announce Type: new Abstract: We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game.
By Chase McDonald, Nathan Tsang, Wesley N. Kerr
We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis.
arXiv:2608. 09389v1 Announce Type: cross Abstract: This note aims to serve as an entry point to the literature on learning in games, a topic with significant theoretical appeal and a wide range of applications -- from machine learning and data science to economics and beyond.
By Panayotis Mertikopoulos
arXiv:2510. 18183v3 Announce Type: replace Abstract: Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning.
By Eason Yu, Tzu Hao Liu, Cl\'ement L. Canonne, Yunke Wang, Chang Xu, Nguyen H. Tran, Stefano V. Albrecht
arXiv:2606. 23995v1 Announce Type: cross Abstract: Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games.
By Tristan Maidment, JB Lanier, Chase McDonald, Nathan Tsang, Eugene Vinitsky, Roy Fox, Albert Wang, Wesley N. Kerr
arXiv:2606. 11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare.
By Wongyu Lee, Francesco Lelli, Omran Ayoub, Massimo Tornatore
arXiv:2606. 20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment.
By Zhewei Kang, Aosong Feng, Sergey Levine, Dawn Song, Xuandong Zhao
arXiv:2606. 06480v1 Announce Type: cross Abstract: Many real-world competitive systems require multiple decision-makers to act simultaneously under shared constraints, limited information, and repeated interaction, as in auctions, resource allocation, and security competition.
By Qintong Xie, Edward Koh, Xavier Cadet, Peter Chin
Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too? Conventional wisdom suggests it should, but recent results show that online RL with a randomly-initialized Q-function can result in highly performant and reliable policies without needing to pretrain the Q-function.