English
Related papers

Related papers: Adaptive Multi-Head Finite-State Gamblers

200 papers

This paper presents online-capable deep learning model for probabilistic vehicle trajectory prediction. We propose a simple encoder-decoder architecture based on multi-head attention. The proposed model generates the distribution of the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-07 Hayoung Kim , Dongchan Kim , Gihoon Kim , Jeongmin Cho , Kunsoo Huh

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Neural and Evolutionary Computing · Computer Science 2019-11-01 C. Daniel Freeman , Luke Metz , David Ha

We introduce a two-player model of reinforcement learning with memory. Past actions of an iterated game are stored in a memory and used to determine player's next action. To examine the behaviour of the model some approximate methods are…

Statistical Mechanics · Physics 2009-11-13 Adam Lipowski , Krzysztof Gontarek , Marcel Ausloos

We investigate the look-ahead capabilities of chess-playing neural networks, specifically focusing on the Leela Chess Zero policy network. We build on the work of Jenner et al. (2024) by analyzing the model's ability to consider future…

Artificial Intelligence · Computer Science 2025-05-29 Diogo Cruz

Learning requires the traversal of inherently distinct cognitive states to produce behavioral adaptation. Yet, tools to explicitly measure these states with non-invasive imaging -- and to assess their dynamics during learning -- remain…

We introduce the first complete formal solution to corrigibility in the off-switch game, with provable guarantees in multi-step, partially observed environments. Our framework consists of five *structurally separate* utility heads --…

Artificial Intelligence · Computer Science 2025-11-20 Aran Nayebi

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

Computation and Language · Computer Science 2026-03-24 Lorenzo Noci , Gregor Bachmann , Seyed-Mohsen Moosavi-Dezfooli , Moin Nabi

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

Machine Learning · Computer Science 2025-11-27 Alex Ning , Yen-Ling Kuo , Gabe Gomes

Models of adaptive bet-hedging commonly adopt insights from Kelly's famous work on optimal gambling strategies and the financial value of information. In particular, such models seek evolutionary solutions that maximize long term average…

Populations and Evolution · Quantitative Biology 2020-03-18 Omri Tal , Tat Dat Tran

We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Through extensive empirical experiments and rigorous theoretical analysis, we demystify the emergence of elegant attention patterns:…

Machine Learning · Computer Science 2025-05-29 Jianliang He , Xintian Pan , Siyu Chen , Zhuoran Yang

In this article, we look at a hat-guessing game, in which each player must guess the color of their own hat while only seeing the hats of the other players. We focus on the case of two hat colors and a countably infinite number of players.…

Probability · Mathematics 2025-10-28 Nathaniel Eldredge

A decision maker observes the evolving state of the world while constantly trying to predict the next state given the history of past states. The ability to benefit from such predictions depends not only on the ability to recognize patters…

Computer Science and Game Theory · Computer Science 2014-09-17 Gilad Bavly , Ron Peretz

We extend the formalism of Conjectural Variations games to Stackelberg games involving multiple leaders and a single follower. To solve these nonconvex games, a common assumption is that the leaders compute their strategies having perfect…

Computer Science and Game Theory · Computer Science 2025-07-24 Francesco Morri , Hélène Le Cadre , Luce Brotcorne

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

In multi-agent reinforcement learning, the problem of learning to act is particularly difficult because the policies of co-players may be heavily conditioned on information only observed by them. On the other hand, humans readily form…

Machine Learning · Computer Science 2021-02-05 Pol Moreno , Edward Hughes , Kevin R. McKee , Bernardo Avila Pires , Théophane Weber

Mean Field Game (MFG) models implicitly assume "rational expectations", meaning that the heterogeneous agents being modeled correctly know all relevant transition probabilities for the complex system they inhabit. When there is common…

Analysis of PDEs · Mathematics 2026-02-26 Benjamin Moll , Lenya Ryzhik

We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle this problem we consider an adaptive allocation rule which at…

Statistics Theory · Mathematics 2020-07-15 Vrettos Moulos

This paper studies sequential information acquisition by an ambiguity-averse decision maker (DM), who decides how long to collect information before taking an irreversible action. The agent optimizes against the worst-case belief and…

Theoretical Economics · Economics 2023-10-06 Sarah Auster , Yeon-Koo Che , Konrad Mierendorff

Gambits are central to human decision-making. Our goal is to provide a theory of Gambits. A Gambit is a combination of psychological and technical factors designed to disrupt predictable play. Chess provides an environment to study gambits…

Theoretical Economics · Economics 2022-04-14 Shiva Maharaj , Nicholas Polson , Christian Turk

Learning problems commonly exhibit an interesting feedback mechanism wherein the population data reacts to competing decision makers' actions. This paper formulates a new game theoretic framework for this phenomenon, called "multi-player…

Computer Science and Game Theory · Computer Science 2022-04-08 Adhyyan Narang , Evan Faulkner , Dmitriy Drusvyatskiy , Maryam Fazel , Lillian J. Ratliff