English
Related papers

Related papers: Dynamic Programming Deconstructed: Transformations…

200 papers

The idea of dynamic programming (DP), proposed by Bellman in the 1950s, is one of the most important algorithmic techniques. However, in parallel, many fundamental and sequentially simple problems become more challenging, and open to a…

Data Structures and Algorithms · Computer Science 2024-05-24 Xiangyun Ding , Yan Gu , Yihan Sun

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing…

Machine Learning · Computer Science 2023-05-26 Taku Yamagata , Ahmed Khalil , Raul Santos-Rodriguez

This article is the starting point of a series of works whose aim is the study of deterministic control problems where the dynamic and the running cost can be completely different in two (or more) complementary domains of the space $\R^N$.…

Analysis of PDEs · Mathematics 2012-09-12 Guy Barles , Ariela Briani , Emmanuel Chasseigne

In this paper, we present a novel maximum entropy formulation of the Differential Dynamic Programming algorithm and derive two variants using unimodal and multimodal value functions parameterizations. By combining the maximum entropy…

Optimization and Control · Mathematics 2022-03-01 Oswin So , Ziyi Wang , Evangelos A. Theodorou

Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of…

Machine Learning · Computer Science 2020-10-12 R. Krishnan , Prasanna Balaprakash

Both the optimal value function and the optimal policy can be used to model an optimal controller based on the duality established by the Bellman equation. Even with this duality, no parametric model has been able to output both policy and…

Systems and Control · Electrical Eng. & Systems 2020-06-02 Jicheng Shi , Yingzhao Lian , Colin N. Jones

This paper explores the integration of Diophantine equations into neural network (NN) architectures to improve model interpretability, stability, and efficiency. By encoding and decoding neural network parameters as integer solutions to…

Machine Learning · Computer Science 2024-09-12 Ronald Katende

In recent years, deep learning has had a profound impact on machine learning and artificial intelligence. At the same time, algorithms for quantum computers have been shown to efficiently solve some problems that are intractable on…

Quantum Physics · Physics 2015-05-25 Nathan Wiebe , Ashish Kapoor , Krysta M. Svore

Quantum computing is emerging as a new computing resource that could be superior to conventional computing for certain classes of optimization problems. However, in principle, most existing approaches to quantum optimization are intended to…

Optimization and Control · Mathematics 2022-01-21 Chin-Yao Chang , Eric Jones , Yiyun Yao , Peter Graf , Rishabh Jain

We present a formalisation of finite Markov decision processes with rewards in the Isabelle theorem prover. We focus on the foundations required for dynamic programming and the use of reinforcement learning agents over such processes. In…

Logic in Computer Science · Computer Science 2021-12-14 Mark Chevallier , Jacques Fleuriot

Engineering system design, viewed as a decision-making process, faces challenges due to complexity and uncertainty. In this paper, we present a framework proposing the use of the Deep Q-learning algorithm to optimize the design of…

Machine Learning · Computer Science 2024-01-01 Ramin Giahi , Cameron A. MacKenzie , Reyhaneh Bijari

This article surveys the burgeoning area at the intersection of dynamical systems theory and algorithms for NP-hard problems. Traditionally, computational complexity and the analysis of non-deterministic polynomial-time (NP)-hard problems…

Optimization and Control · Mathematics 2020-05-12 Tuhin Sahai

The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator.…

Machine Learning · Computer Science 2019-05-21 Zhao Song , Ronald E. Parr , Lawrence Carin

Recently, it has been proven that evolutionary algorithms produce good results for a wide range of combinatorial optimization problems. Some of the considered problems are tackled by evolutionary algorithms that use a representation which…

Neural and Evolutionary Computing · Computer Science 2013-01-18 Benjamin Doerr , Anton Eremeev , Frank Neumann , Madeleine Theile , Christian Thyssen

Recently, there has been a surge of interest in analyzing the non-asymptotic behavior of model-free reinforcement learning algorithms. However, the performance of such algorithms in non-ideal environments, such as in the presence of…

Machine Learning · Computer Science 2024-09-06 Sreejeet Maity , Aritra Mitra

While it seems possible that quantum computers may allow for algorithms offering a computational speed-up over classical algorithms for some problems, the issue is poorly understood. We explore this computational speed-up by investigating…

Quantum Physics · Physics 2010-06-09 Alastair A. Abbott , Cristian S. Calude

Most continuous mathematical formulations arising in science and engineering can only be solved numerically and therefore approximately. We shall always assume that we're dealing with a numerical approximation to the solution. There are two…

Quantum Physics · Physics 2007-12-10 A. Papageorgiou , J. F. Traub

Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…

Machine Learning · Computer Science 2020-01-10 Yihao Feng , Lihong Li , Qiang Liu

We consider stochastic dynamic programming problems with high-dimensional, discrete state-spaces and finite, discrete-time horizons that prohibit direct computation of the value function from a given Bellman equation for all states and time…

Optimization and Control · Mathematics 2020-06-05 Denis Lebedev , Paul Goulart , Kostas Margellos

Many learning algorithms are formulated in terms of finding model parameters which minimize a data-fitting loss function plus a regularizer. When the regularizer involves the l0 pseudo-norm, the resulting regularization path consists of a…

Machine Learning · Computer Science 2020-03-06 Toby Hocking , Joseph Vargovich