English
Related papers

Related papers: Autoregressive Dynamics Models for Offline Policy …

200 papers

Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…

Machine Learning · Computer Science 2022-03-04 Lukas P. Fröhlich , Maksym Lefarov , Melanie N. Zeilinger , Felix Berkenkamp

We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of reference, removing temporal correlations, and simplifying the…

Machine Learning · Computer Science 2022-03-09 Joseph Marino , Lei Chen , Jiawei He , Stephan Mandt

Autoregressive models are a class of generative model that probabilistically predict the next output of a sequence based on previous inputs. The autoregressive sequence is by definition one-dimensional (1D), which is natural for language…

Machine Learning · Computer Science 2024-08-29 Yi Hong Teoh , Roger G. Melko

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introduce an inference…

Machine Learning · Computer Science 2026-05-21 Rohan Deb , Stephen J. Wright , Arindam Banerjee

Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model-based reinforcement learning algorithm that represents…

Machine Learning · Computer Science 2023-11-01 Lenart Treven , Jonas Hübotter , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Despite the increasing popularity of policy gradient methods, they are yet to be widely utilized in sample-scarce applications, such as robotics. The sample efficiency could be improved by making best usage of available information. As a…

Machine Learning · Computer Science 2023-11-03 Qingfeng Lan , Samuele Tosatto , Homayoon Farrahi , A. Rupam Mahmood

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true…

Machine Learning · Computer Science 2026-05-13 Nadav Timor , Ravid Shwartz-Ziv , Micah Goldblum , Yann LeCun , David Harel

In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment.…

Machine Learning · Computer Science 2019-11-26 Alex Irpan , Kanishka Rao , Konstantinos Bousmalis , Chris Harris , Julian Ibarz , Sergey Levine

Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through…

Machine Learning · Computer Science 2025-01-22 Chuning Zhu , Xinqi Wang , Tyler Han , Simon S. Du , Abhishek Gupta

Model-based reinforcement learning (MBRL) algorithms learn a dynamics model from collected data and apply it to generate synthetic trajectories to enable faster learning. This is an especially promising paradigm in offline reinforcement…

Machine Learning · Computer Science 2024-08-21 Padmanaba Srinivasan , William Knottenbelt

We present a data-driven nonintrusive model order reduction method for dynamical systems with moving boundaries. The proposed method draws on the proper orthogonal decomposition, Gaussian process regression, and moving least squares…

Computational Engineering, Finance, and Science · Computer Science 2021-03-18 Zhan Ma , Wenxiao Pan

This paper investigates options to complement a diesel engine airpath feedback controller with a feedforward. The control objective is to track the intake manifold pressure and exhaust gas recirculation (EGR) rate targets by manipulating…

Systems and Control · Electrical Eng. & Systems 2022-05-12 Jiadi Zhang , Mohammad Reza Amini , Ilya Kolmanovsky , Munechika Tsutsumi , Hayato Nakada

Conditional diffusion models provide a natural framework for probabilistic prediction of dynamical systems and have been successfully applied to fluid dynamics and weather prediction. However, in many settings, the available information at…

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generating new outputs, one…

Model-Based Reinforcement Learning involves learning a \textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \textit{planner}. Much of the recent research along these lines presents a…

Learning a precise dynamics model can be crucial for offline reinforcement learning, which, unfortunately, has been found to be quite challenging. Dynamics models that are learned by fitting historical transitions often struggle to…

Machine Learning · Computer Science 2023-10-10 Fan-Ming Luo , Tian Xu , Xingchen Cao , Yang Yu

Projection-based reduced order models rely on offline-online model decomposition, where the data-based energetic spatial basis is used in the expensive offline stage to obtain equations of reduced states that evolve in time during the…

Fluid Dynamics · Physics 2024-02-01 Aviral Prakash , Yongjie Jessica Zhang

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy…

Machine Learning · Computer Science 2023-04-06 Haoran Xu , Li Jiang , Jianxiong Li , Xianyuan Zhan

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…

We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. It provides explicit near-optimal policies for any reward specified a posteriori. During an unsupervised phase, we use…

Machine Learning · Computer Science 2021-10-12 Ahmed Touati , Yann Ollivier