English
Related papers

Related papers: Closed-loop deep learning: generating forward mode…

200 papers

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Machine Learning · Computer Science 2026-02-17 Taiwei Shi , Sihao Chen , Bowen Jiang , Linxin Song , Longqi Yang , Jieyu Zhao

Deep reinforcement learning (DRL) has recently shown its success in tackling complex combinatorial optimization problems. When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to…

Artificial Intelligence · Computer Science 2022-02-15 Zizhen Zhang , Zhiyuan Wu , Hang Zhang , Jiahai Wang

Action planning using learned and differentiable forward models of the world is a general approach which has a number of desirable properties, including improved sample complexity over model-free RL methods, reuse of learned models across…

Artificial Intelligence · Computer Science 2018-04-05 Mikael Henaff , William F. Whitney , Yann LeCun

This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor lead times, lost sales, correlated demand, and price matching. While this dynamic program has…

Machine Learning · Computer Science 2022-11-30 Dhruv Madeka , Kari Torkkola , Carson Eisenach , Anna Luo , Dean P. Foster , Sham M. Kakade

Achieving both high speed and precision in robot operations is a significant challenge for social implementation. While factory robots excel at predefined tasks, they struggle with environment-specific actions like cleaning and cooking.…

Robotics · Computer Science 2024-08-21 Masaki Yoshikawa , Hiroshi Ito , Tetsuya Ogata

Motion planning is an essential component in most of today's robotic applications. In this work, we consider the learning setting, where a set of solved motion planning problems is used to improve the efficiency of motion planning on…

Robotics · Computer Science 2019-06-04 Tom Jurgenson , Aviv Tamar

Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning. Backpropagation, or reverse-mode differentiation, is a special case within the general family of automatic…

Machine Learning · Computer Science 2022-02-18 Atılım Güneş Baydin , Barak A. Pearlmutter , Don Syme , Frank Wood , Philip Torr

In complex real-world tasks such as robotic manipulation and autonomous driving, collecting expert demonstrations is often more straightforward than specifying precise learning objectives and task descriptions. Learning from expert data can…

Robotics · Computer Science 2025-05-05 Daulet Baimukashev , Gokhan Alcan , Kevin Sebastian Luck , Ville Kyrki

Conventional deep models predict a test sample with a single forward propagation, which, however, may not be sufficient for predicting hard-classified samples. On the contrary, we human beings may need to carefully check the sample many…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Shuaicheng Niu , Jiaxiang Wu , Yifan Zhang , Guanghui Xu , Haokun Li , Peilin Zhao , Junzhou Huang , Yaowei Wang , Mingkui Tan

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate…

Computation and Language · Computer Science 2026-02-06 Arip Asadulaev , Rayan Banerjee , Fakhri Karray , Martin Takac

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation…

We demonstrate that deep reinforcement learning (deep RL) provides a highly effective strategy for the control and self-tuning of optical systems. Deep RL integrates the two leading machine learning architectures of deep neural networks and…

Signal Processing · Electrical Eng. & Systems 2020-06-11 Chang Sun , Eurika Kaiser , Steven L. Brunton , J. Nathan Kutz

Deep reinforcement Learning for end-to-end driving is limited by the need of complex reward engineering. Sparse rewards can circumvent this challenge but suffers from long training time and leads to sub-optimal policy. In this work, we…

Robotics · Computer Science 2021-08-03 Pranav Agarwal , Pierre de Beaucorps , Raoul de Charette

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Cryptography and Security · Computer Science 2025-03-28 Dorde Popovic , Amin Sadeghi , Ting Yu , Sanjay Chawla , Issa Khalil

A deep learning system typically suffers from a lack of reproducibility that is partially rooted in hardware or software implementation details. The irreproducibility leads to skepticism in deep learning technologies and it can hinder them…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Jiahao Pang , Muhammad Asad Lodhi , Junghyun Ahn , Yuning Huang , Dong Tian

We propose Sideways, an approximate backpropagation scheme for training video models. In standard backpropagation, the gradients and activations at every computation step through the model are temporally synchronized. The forward…

Machine Learning · Computer Science 2020-04-01 Mateusz Malinowski , Grzegorz Swirszcz , Joao Carreira , Viorica Patraucean

Reinforcement learning has received high research interest for developing planning approaches in automated driving. Most prior works consider the end-to-end planning task that yields direct control commands and rarely deploy their algorithm…

Robotics · Computer Science 2023-07-31 Marvin Klimke , Benjamin Völz , Michael Buchholz

Traditional planning and control methods could fail to find a feasible trajectory for an autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle-free volume in spacetime is very small in these scenarios…

Robotics · Computer Science 2022-12-29 Dhruv Mauria Saxena , Sangjae Bae , Alireza Nakhaei , Kikuo Fujimura , Maxim Likhachev

A fundamental challenge in car-following modeling lies in accurately representing the multi-scale complexity of driving behaviors, particularly the intra-driver heterogeneity where a single driver's actions fluctuate dynamically under…

Machine Learning · Computer Science 2025-06-09 Shirui Zhou , Jiying Yan , Junfang Tian , Tao Wang , Yongfu Li , Shiquan Zhong

System identification, also known as learning forward models, transfer functions, system dynamics, etc., has a long tradition both in science and engineering in different fields. Particularly, it is a recurring theme in Reinforcement…