English
Related papers

Related papers: Evolutionary Transfer Learning for Dragonchess

200 papers

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across…

Machine Learning · Computer Science 2022-06-22 Xingyu Liu , Deepak Pathak , Kris M. Kitani

This thesis presents some geometric insights into three different types of two player prediction games -- namely general learning task, prediction with expert advice, and online convex optimization. These games differ in the nature of the…

Machine Learning · Computer Science 2018-05-23 Parameswaran Kamalaruban

Metaheuristic search methods have proven to be essential tools for tackling complex optimization challenges, but their full potential is often constrained by conventional algorithmic frameworks. In this paper, we introduce a novel approach…

Artificial Intelligence · Computer Science 2024-10-23 Abdel-Rahman Hedar , Alaa E. Abdel-Hakim , Wael Deabes , Youseef Alotaibi , Kheir Eddine Bouazza

Heuristics are widely used for dealing with complex search and optimization problems. However, manual design of heuristics can be often very labour extensive and requires rich working experience and knowledge. This paper proposes Evolution…

Neural and Evolutionary Computing · Computer Science 2024-06-04 Fei Liu , Xialiang Tong , Mingxuan Yuan , Xi Lin , Fu Luo , Zhenkun Wang , Zhichao Lu , Qingfu Zhang

Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and precise fine-grained control. However, the interface between…

Robotics · Computer Science 2025-02-24 Haibo Zhao , Dian Wang , Yizhe Zhu , Xupeng Zhu , Owen Howell , Linfeng Zhao , Yaoyao Qian , Robin Walters , Robert Platt

There are an increasing number of domains in which artificial intelligence (AI) systems both surpass human ability and accurately model human behavior. This introduces the possibility of algorithmically-informed teaching in these domains…

Artificial Intelligence · Computer Science 2024-11-04 Zhenwei Tang , Difan Jiao , Reid McIlroy-Young , Jon Kleinberg , Siddhartha Sen , Ashton Anderson

Evolutionary game theory classically investigates which behavioral patterns are evolutionarily successful in a single game. More recently, a number of contributions have studied the evolution of preferences instead: which subjective…

Computer Science and Game Theory · Computer Science 2015-05-27 Paolo Galeazzi , Michael Franke

We present a novel algorithm -- convex natural evolutionary strategies (CoNES) -- for optimizing high-dimensional blackbox functions by leveraging tools from convex optimization and information geometry. CoNES is formulated as an…

Machine Learning · Computer Science 2020-07-21 Sushant Veer , Anirudha Majumdar

We investigate the problem of transferring an expert policy from a source robot to multiple different robots. To solve this problem, we propose a method named $Meta$-$Evolve$ that uses continuous robot evolution to efficiently transfer the…

Robotics · Computer Science 2024-05-07 Xingyu Liu , Deepak Pathak , Ding Zhao

Situations involving cooperative behaviour are widespread among animals and humans alike. Game theory and evolutionary dynamics have provided the theoretical and computational grounds to understand what are the mechanisms that allow for…

Physics and Society · Physics 2020-09-17 Felipe Maciel Cardoso , Carlos Gracia-Lazaro , Yamir Moreno

In Keynesian Beauty Contests notably modeled by p-guessing games, players try to guess the average of guesses multiplied by p. Convergence of plays to Nash equilibrium has often been justified by agents' learning. However, interrogations…

General Economics · Economics 2021-03-29 Aymeric Vie

Artificial neural networks learn how to solve new problems through a computationally intense and time consuming process. One way to reduce the amount of time required is to inject preexisting knowledge into the network. To make use of past…

Neural and Evolutionary Computing · Computer Science 2015-09-10 Cosmin Stamate , George D. Magoulas , Michael S. C. Thomas

In this paper, we propose the use of traditional animations, heuristic behavior and reinforcement learning in the creation of intelligent characters for computational media. The traditional animation and heuristic gives artistic control…

Machine Learning · Computer Science 2021-12-21 Caio Souza , Luiz Velho

We study a modified prisoner's dilemma game taking place on two-dimensional disordered square lattices. The players are pure strategists and can either cooperate or defect with their immediate neighbors. In the generations each player…

Physics and Society · Physics 2007-05-23 Zhi-Xi Wu , Xin-Jian Xu , Zi-Gang Huang , Sheng-Jun Wang , Ying-Hai Wang

When globally optimal solutions of complicated optimization problems cannot be located by evolutionary algorithms (EAs) in polynomial expected running time, the hitting time/running time analysis is not flexible enough to accommodate the…

Neural and Evolutionary Computing · Computer Science 2020-12-01 Cong Wang , Yu Chen , Jun He , Chengwang Xie

Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of…

Neural and Evolutionary Computing · Computer Science 2022-02-23 Youssef Diouane , Aurelien Lucchi , Vihang Patil

We conducted a laboratory experiment involving human subjects to test the theoretical hypothesis that equilibrium selection can be impacted by manipulating the games dynamics process, by using modern control theory. Our findings indicate…

General Economics · Economics 2024-11-12 Wang Zhijian , Shan Lixia , Yao Qinmei , Wang Yijia

We introduce Genetic AI, a novel method for multi-objective optimization without external parameters or predefined weights. The method can be applied to all problems that can be formulated in matrix form and allows for a data-less training…

Neural and Evolutionary Computing · Computer Science 2025-05-09 Philipp Wissgott

Complete tree search is a highly effective method for tackling MIP problems, and over the years, a plethora of branching heuristics have been introduced to further refine the technique for varying problems. Recently, portfolio algorithms…

Artificial Intelligence · Computer Science 2013-07-19 Giovanni Di Liberto , Serdar Kadioglu , Kevin Leo , Yuri Malitsky

This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex…

Machine Learning · Computer Science 2023-03-13 Nikolaus Hansen