English
Related papers

Related papers: Universal Learning of Repeated Matrix Games

200 papers

This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it…

Machine Learning · Computer Science 2007-05-23 Jan Poland , Marcus Hutter

We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy, while the other, the optimizer, is a rational utility maximizer. We consider general Bayesian games, where the payoffs of both…

Machine Learning · Computer Science 2022-05-19 Yishay Mansour , Mehryar Mohri , Jon Schneider , Balasubramanian Sivan

We study learning dynamics induced by strategic agents who repeatedly play a game with an unknown payoff-relevant parameter. In each step, an information system estimates a belief distribution of the parameter based on the players'…

Systems and Control · Electrical Eng. & Systems 2020-10-20 Manxi Wu , Saurabh Amin , Asuman Ozdaglar

Despite much research targeted at enabling conventional machine learning models to continually learn tasks and data distributions sequentially without forgetting the knowledge acquired, little effort has been devoted to account for more…

Machine Learning · Computer Science 2021-06-11 Sandra Servia-Rodriguez , Cecilia Mascolo , Young D. Kwon

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Computer Science 2014-08-12 Aristide Tossou , Christos Dimitrakakis

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

Machine Learning · Statistics 2013-07-16 Aristide C. Y. Tossou , Christos Dimitrakakis

Robots can learn to imitate humans by inferring what the human is optimizing for. One common framework for this is Bayesian reward learning, where the robot treats the human's demonstrations and corrections as observations of their…

Robotics · Computer Science 2023-10-20 Joshua Hoegerman , Dylan P. Losey

We investigate symmetric equilibria of mutual reinforcement learning when both players alternately learn the optimal memory-two strategies against the opponent in the repeated prisoners' dilemma game. We provide a necessary condition for…

Physics and Society · Physics 2023-01-03 Masahiko Ueda

Many state-of-the-art reinforcement learning (RL) algorithms typically assume that the environment is an ergodic Markov Decision Process (MDP). In contrast, the field of universal reinforcement learning (URL) is concerned with algorithms…

Artificial Intelligence · Computer Science 2017-05-31 John Aslanides , Jan Leike , Marcus Hutter

Traditional imitation learning provides a set of methods and algorithms to learn a reward function or policy from expert demonstrations. Learning from demonstration has been shown to be advantageous for navigation tasks as it allows for…

Robotics · Computer Science 2021-08-03 Christian Ellis , Maggie Wigness , John G. Rogers , Craig Lennon , Lance Fiondella

We consider a number of questions related to tradeoffs between reward and regret in repeated gameplay between two agents. To facilitate this, we introduce a notion of $\textit{generalized equilibrium}$ which allows for asymmetric regret…

Computer Science and Game Theory · Computer Science 2023-12-19 William Brown , Jon Schneider , Kiran Vodrahalli

We study the fundamental problem of learning a marginally stable unknown nonlinear dynamical system. We describe an algorithm for this problem, based on the technique of spectral filtering, which learns a mapping from past observations to…

Machine Learning · Computer Science 2025-08-19 Evan Dogariu , Anand Brahmbhatt , Elad Hazan

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a…

Machine Learning · Computer Science 2019-04-25 Yu Chen , Tom Diethe , Neil Lawrence

We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training, or input transformation, we instead phrase it as a…

Machine Learning · Computer Science 2018-09-27 Julien Perolat , Mateusz Malinowski , Bilal Piot , Olivier Pietquin

Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm…

Machine Learning · Computer Science 2019-08-14 Philip Bontrager , Ahmed Khalifa , Damien Anderson , Matthew Stephenson , Christoph Salge , Julian Togelius

In the realm of supervised learning, Bayesian learning has shown robust predictive capabilities under input and parameter perturbations. Inspired by these findings, we demonstrate the robustness properties of Bayesian learning in the…

Machine Learning · Computer Science 2022-05-17 Nardos Ayele Ashenafi , Wankun Sirichotiyakul , Aykut C. Satici

We present two variants of a multi-agent reinforcement learning algorithm based on evolutionary game theoretic considerations. The intentional simplicity of one variant enables us to prove results on its relationship to a system of ordinary…

Machine Learning · Computer Science 2024-05-29 Johann Bauer , Sheldon West , Eduardo Alonso , Mark Broom

We consider distributed learning problem in games with an unknown cost-relevant parameter, and aim to find the Nash equilibrium while learning the true parameter. Inspired by the social learning literature, we propose a distributed…

Optimization and Control · Mathematics 2023-03-14 Shijie Huang , Jinlong Lei , Yiguang Hong

Human cooperation depends on how accurately we infer others' motives--how much they value fairness, generosity, or self-interest from the choices they make. We model that process in binary dictator games, which isolate moral trade-offs…

Neurons and Cognition · Quantitative Biology 2025-11-12 Gregory Stanley , Jun Zhang , Rick Lewis

In this paper we proposed reinforcement learning algorithms with the generalized reward function. In our proposed method we use Q-learning and SARSA algorithms with generalised reward function to train the reinforcement learning agent. We…

Artificial Intelligence · Computer Science 2016-02-17 Harshit Sethy , Amit Patel