This paper shows that a threshold in decision capacity governs collapse in self-play reinforcement learning agents under asymmetric rule perturbations. Eliminating all positive-reach contingent decisions causes rapid convergence to a deterministic exploitation attractor, while preserving even a single such decision prevents this collapse.
This paper investigates truthful online preference aggregation for fine-tuning Large Language Models (LLMs) in mobile crowdsourcing. It proposes a novel online weighted aggregation mechanism to address strategic misreporting by workers, modeling the process as a dynamic Bayesian game. The goal is to overcome existing approaches that fail to identify the most accurate worker and result in linear regret.
This paper introduces "Quantum Frog", a two-player cooperative game built on a novel quantized-time mechanic, inspired by Frogger. It uses reinforcement learning to analyze game difficulty scaling, optimal policies, and emergent cooperative strategies.
The SEM analysis argues that bidding has evolved into a "survival tax" and negative-sum game, pushing companies into "corporate charity." Advanced players now focus on "cognitive arbitrage," correcting user perceptions and building trust for asymmetric growth, necessitating strict ROI auditing and algorithm understanding.
Este artigo estima com alta precisão a complexidade do espaço de estados do jogo Shogi (xadrez japonês), um problema desafiador. Utilizando o método Monte Carlo e uma nova busca reversa, os autores estimam o número de posições legais em $6.55 \times 10^{68}$.
Apesar de séculos de estudo e do poder computacional moderno, o xadrez permanece sem solução, pois não se sabe o resultado final com jogadas perfeitas devido à sua complexidade astronômica. O artigo define 'resolver um jogo' em computação, diferenciando entre soluções fracas e fortes.
The article explores recent AI developments in May 2026, highlighting discussions on game theoretic responses to AI adoption, including concerns about the creation of inferior products and misuse by non-experts. It also briefly touches upon niche applications like AI-powered guitar pedals.