arXiv AI

Self-Play Reinforcement Learning under Imperfect Information in Big 2

arXiv:2605. 28863v2 Announce Type: replace-cross Abstract: Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents.

Hugging Face Trending Papers
Jul 7

FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

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 AI
Jun 24

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

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 Machine Learning
Jun 5

DNQ: Deep Nash Q-Network for Partially Observable n-Player Games

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
Hugging Face Trending Papers
Jul 29

Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

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.