English
Related papers

Related papers: Backpropagation through Time and Space: Learning N…

200 papers

Policy iteration (PI) is a recursive process of policy evaluation and improvement for solving an optimal decision-making/control problem, or in other words, a reinforcement learning (RL) problem. PI has also served as the fundamental for…

Artificial Intelligence · Computer Science 2021-04-06 Jaeyoung Lee , Richard S. Sutton

We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process…

Machine Learning · Computer Science 2026-02-04 Seiji Shaw , Travis Manderson , Chad Kessens , Nicholas Roy

Advection-dominated dynamical systems, characterized by partial differential equations, are found in applications ranging from weather forecasting to engineering design where accuracy and robustness are crucial. There has been significant…

Computational Physics · Physics 2020-06-29 Romit Maulik , Bethany Lusch , Prasanna Balaprakash

We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each…

Multiagent Systems · Computer Science 2021-11-02 Kuo Li , Qing-Shan Jia

Transfer learning has recently shown significant performance across various tasks involving deep neural networks. In these transfer learning scenarios, the prior distribution for downstream data becomes crucial in Bayesian model averaging…

Machine Learning · Computer Science 2024-03-13 Hyungi Lee , Giung Nam , Edwin Fong , Juho Lee

Deep State Space Models (SSMs) reignite physics-grounded compute paradigms, as RNNs could natively be embodied into dynamical systems. This calls for dedicated learning algorithms obeying to core physical principles, with efficient…

Machine Learning · Computer Science 2025-06-06 Guillaume Pourcel , Maxence Ernoult

In this paper, we propose a Model-Based Reinforcement Learning (MBRL) algorithm for Partially Measurable Systems (PMS), i.e., systems where the state can not be directly measured, but must be estimated through proper state observers. The…

Robotics · Computer Science 2021-01-22 Fabio Amadio , Alberto Dalla Libera , Ruggero Carli , Daniel Nikovski , Diego Romeres

We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language -- linear temporal logic (LTL) -- and can specify a…

Artificial Intelligence · Computer Science 2021-07-07 Pashootan Vaezipoor , Andrew Li , Rodrigo Toro Icarte , Sheila McIlraith

Autonomous multi-agent systems such as hospital robots and package delivery drones often operate in highly uncertain environments and are expected to achieve complex temporal task objectives while ensuring safety. While learning-based…

Multiagent Systems · Computer Science 2024-11-19 Sheryl Paul , Anand Balakrishnan , Xin Qin , Jyotirmoy V. Deshmukh

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…

Machine Learning · Computer Science 2019-05-16 Yash Chandak , Georgios Theocharous , James Kostas , Scott Jordan , Philip S. Thomas

Recurrent networks are typically trained with backpropagation through time (BPTT). However, BPTT requires storing the history of all states in the network and then replaying them sequentially backwards in time. This computation appears…

Machine Learning · Computer Science 2026-01-01 Beren Millidge

This paper proposes a multi-agent reinforcement learning (MARL) approach to learn dynamic dispatching strategies, which is crucial for optimizing throughput in material handling systems across diverse industries. To benchmark our method, we…

Machine Learning · Computer Science 2024-09-30 Xian Yeow Lee , Haiyan Wang , Daisuke Katsumata , Takaharu Matsui , Chetan Gupta

Training recurrent neural networks (RNNs) with standard backpropagation through time (BPTT) can be challenging, especially in the presence of long input sequences. A practical alternative to reduce computational and memory overhead is to…

Machine Learning · Computer Science 2026-02-12 Julian D. Schiller , Malte Heinrich , Victor G. Lopez , Matthias A. Müller

Reinforcement learning (RL) algorithms allow artificial agents to improve their selection of actions to increase rewarding experiences in their environments. Temporal Difference (TD) Learning -- a model-free RL method -- is a leading…

Machine Learning · Computer Science 2019-09-05 Jacob Rafati , David C. Noelle

We study reinforcement learning (RL) in the setting of continuous time and space, for an infinite horizon with a discounted objective and the underlying dynamics driven by a stochastic differential equation. Built upon recent advances in…

Machine Learning · Computer Science 2023-10-19 Hanyang Zhao , Wenpin Tang , David D. Yao

Simulators driven by deep learning are gaining popularity as a tool for efficiently emulating accurate but expensive numerical simulators. Successful applications of such neural simulators can be found in the domains of physics, chemistry,…

Quantitative Methods · Quantitative Biology 2022-11-04 Koen Minartz , Yoeri Poels , Vlado Menkovski

We study the problem of learning to stabilize (LTS) a linear time-invariant (LTI) system. Policy gradient (PG) methods for control assume access to an initial stabilizing policy. However, designing such a policy for an unknown system is one…

Machine Learning · Computer Science 2025-05-07 Leonardo F. Toso , Lintao Ye , James Anderson

Humans and animals solve a difficult problem much more easily when they are presented with a sequence of problems that starts simple and slowly increases in difficulty. We explore this idea in the context of reinforcement learning. Rather…

Machine Learning · Computer Science 2019-12-06 Jan Malte Lichtenberg , Özgür Şimşek

We propose a multilevel tensor-train (TT) framework for solving nonlinear partial differential equations (PDEs) in a global space-time formulation. While space-time TT solvers have demonstrated significant potential for compressed…

Numerical Analysis · Mathematics 2026-02-10 N. R. Rapaka , R. Peddinti , E. Tiunov , N. J. Faraj , A. N. Alkhooori , L. Aolita , Y. Addad , M. K. Riahi

Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain…

Machine Learning · Computer Science 2017-04-28 Vivek Veeriah , Shangtong Zhang , Richard S. Sutton