English
Related papers

Related papers: Solving Atari Games Using Fractals And Entropy

200 papers

Inverse game theory is utilized to infer the cost functions of all players based on game outcomes. However, existing inverse game theory methods do not consider the learner as an active participant in the game, which could significantly…

Computer Science and Game Theory · Computer Science 2025-10-20 Jianguo Chen , Jinlong Lei , Biqiang Mu , Yiguang Hong , Hongsheng Qi

Monte Carlo simulations are widely employed to measure the physical properties of glass-forming liquids in thermal equilibrium. Combined with local Monte Carlo moves, the Metropolis algorithm can also be used to simulate the relaxation…

Statistical Mechanics · Physics 2024-09-23 Ludovic Berthier , Federico Ghimenti Frédéric van Wijland

Quantitative theory of interbilayer interactions is essential to interpret x-ray scattering data and to elucidate these interactions for biologically relevant systems. For this purpose Monte Carlo simulations have been performed to obtain…

Biological Physics · Physics 2009-10-31 Nikolai Gouliaev , John F. Nagle

Do you remember your first video game console? We remember ours. Decades ago, they provided hours of entertainment. Now, we have repurposed them to solve dynamic and stochastic optimization problems. With deep reinforcement learning methods…

Machine Learning · Computer Science 2024-09-25 Nicholas D. Kullman , Nikita Dudorov , Jorge E. Mendoza , Martin Cousineau , Justin C. Goodson

Molecular motors are in charge of almost every process in the life cycle of cells, such as protein synthesis, DNA replication, and cell locomotion, hence being of crucial importance for understanding the cellular dynamics. However, given…

Statistical Mechanics · Physics 2025-09-05 Adrián Nadal-Rosa , Gonzalo Manzano

We present a method of endowing agents in an agent-based model (ABM) with sophisticated cognitive capabilities and a naturally tunable level of intelligence. Often, ABMs use random behavior or greedy algorithms for maximizing objectives…

Artificial Intelligence · Computer Science 2018-07-31 Bryan Head , Uri Wilensky

Monte Carlo simulations of a system whose action has an imaginary part are considered to be extremely difficult. We propose a new approach to this `complex-action problem', which utilizes a factorization property of distribution functions.…

High Energy Physics - Theory · Physics 2008-11-26 K. N. Anagnostopoulos , J. Nishimura

Mean-field games (MFGs) study the Nash equilibrium of systems with a continuum of interacting agents, which can be formulated as the fixed-point of optimal control problems. They provide a unified framework for a variety of applications,…

Machine Learning · Statistics 2025-12-02 Jiajia Yu , Junghwan Lee , Yao Xie , Xiuyuan Cheng

Decentralized online planning can be an attractive paradigm for cooperative multi-agent systems, due to improved scalability and robustness. A key difficulty of such approach lies in making accurate predictions about the decisions of other…

Artificial Intelligence · Computer Science 2020-11-11 Aleksander Czechowski , Frans A. Oliehoek

We introduce a system called Amorphous Fortress -- an abstract, yet spatial, open-ended artificial life simulation. In this environment, the agents are represented as finite-state machines (FSMs) which allow for multi-agent interaction…

Artificial Intelligence · Computer Science 2023-06-26 M Charity , Dipika Rajesh , Sam Earle , Julian Togelius

Exponential observables, formulated as $\log \langle e^{\hat{X}}\rangle$ where $\hat{X}$ is an extensive quantity, play a critical role in study of quantum many-body systems, examples of which include the free-energy and entanglement…

Strongly Correlated Electrons · Physics 2024-05-28 Xu Zhang , Gaopei Pan , Bin-Bin Chen , Kai Sun , Zi Yang Meng

Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically…

Multiagent Systems · Computer Science 2026-05-11 Yuxuan Zhao , Sijia Chen , Ningxin Su

In this paper, we explore and compare multiple algorithms for solving the complex strategy game of Terra Mystica, hereafter abbreviated as TM. Previous work in the area of super-human game-play using AI has proven effective, with recent…

Multiagent Systems · Computer Science 2021-02-23 Luis Perez

We present the design of a competitive artificial intelligence for Scopone, a popular Italian card game. We compare rule-based players using the most established strategies (one for beginners and two for advanced players) against players…

Artificial Intelligence · Computer Science 2018-07-30 Stefano Di Palma , Pier Luca Lanzi

We introduce a recursive AlphaZero-style Monte--Carlo tree search algorithm, "RMCTS". The advantage of RMCTS over AlphaZero's MCTS-UCB is speed. In RMCTS, the search tree is explored in a breadth-first manner, so that network inferences…

Artificial Intelligence · Computer Science 2026-01-12 Keith Frankston , Benjamin Howard

Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based…

Machine Learning · Computer Science 2019-03-05 Giuseppe Cuccu , Julian Togelius , Philippe Cudre-Mauroux

Policy-guided Monte Carlo is an adaptive method to simulate classical interacting systems. It adjusts the proposal distribution of the Metropolis-Hastings algorithm to maximize the sampling efficiency, using a formalism inspired by…

Soft Condensed Matter · Physics 2024-08-23 Leonardo Galliano , Riccardo Rende , Daniele Coslovich

Monte Carlo Tree Search (MCTS) has recently been successfully used to create strategies for playing imperfect-information games. Despite its popularity, there are no theoretic results that guarantee its convergence to a well-defined…

Computer Science and Game Theory · Computer Science 2015-09-02 Vojtěch Kovařík , Viliam Lisý

We present Doubly Robust Monte Carlo Tree Search (DR-MCTS), a novel algorithm that integrates Doubly Robust (DR) off-policy estimation into Monte Carlo Tree Search (MCTS) to enhance sample efficiency and decision quality in complex…

Machine Learning · Statistics 2025-02-05 Manqing Liu , Andrew L. Beam

We are concerned with a distributed approach to solve multi-cluster games arising in multi-agent systems. In such games, agents are separated into distinct clusters. The agents belonging to the same cluster cooperate with each other to…

Systems and Control · Electrical Eng. & Systems 2022-03-14 Jan Zimmermann , Tatiana Tatarenko , Volker Willert , Jürgen Adamy
‹ Prev 1 8 9 10 Next ›