English
Related papers

Related papers: HG-DAgger: Interactive Imitation Learning with Hum…

200 papers

Imitation learning has been widely applied to various autonomous systems thanks to recent development in interactive algorithms that address covariate shift and compounding errors induced by traditional approaches like behavior cloning.…

Machine Learning · Computer Science 2024-05-03 Xiatao Sun , Shuo Yang , Mingyan Zhou , Kunpeng Liu , Rahul Mangharam

Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imitation learning often provides a more convenient and…

Artificial Intelligence · Computer Science 2024-03-20 Jianlan Luo , Perry Dong , Yuexiang Zhai , Yi Ma , Sergey Levine

Interactive Imitation Learning deals with training a novice policy from expert demonstrations in an online fashion. The established DAgger algorithm trains a robust novice policy by alternating between interacting with the environment and…

Systems and Control · Electrical Eng. & Systems 2025-10-02 Julian Lemmel , Manuel Kranzl , Adam Lamine , Philipp Neubauer , Radu Grosu , Sophie A. Neubauer

While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by continually aggregating training data…

Artificial Intelligence · Computer Science 2017-09-20 Kunal Menda , Katherine Driggs-Campbell , Mykel J. Kochenderfer

While imitation learning is often used in robotics, the approach frequently suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by aggregating training data from both the expert…

Machine Learning · Computer Science 2019-07-23 Kunal Menda , Katherine Driggs-Campbell , Mykel J. Kochenderfer

DAgger is an imitation algorithm that aggregates its original datasets by querying the expert on all samples encountered during training. In order to reduce the number of samples queried, we propose a modification to DAgger, known as…

Machine Learning · Computer Science 2023-01-05 Akash Haridas , Karim Hamadeh , Samarendra Chandan Bindu Dash

Imitation learning is a powerful paradigm for training robotic policies, yet its performance is limited by compounding errors: minor policy inaccuracies could drive robots into unseen out-of-distribution (OOD) states in the training set,…

Robotics · Computer Science 2026-04-14 Anlan Yu , Zaishu Chen , Peili Song , Zhiqing Hong , Haotian Wang , Desheng Zhang , Tian He , Yi Ding , Daqing Zhang

Collecting human demonstrations via teleoperation is a common approach for teaching robots task-specific skills. However, when only a limited number of demonstrations are available, policies are prone to entering out-of-distribution (OOD)…

Robotics · Computer Science 2026-04-07 Rui Yan , Zaitian Gongye , Lars Paulsen , Xuxin Cheng , Xiaolong Wang

Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…

Robotics · Computer Science 2020-12-15 Yaru Niu , Yijun Gu

A common failure mode for policies trained with imitation is compounding execution errors at test time. When the learned policy encounters states that are not present in the expert demonstrations, the policy fails, leading to degenerate…

Robotics · Computer Science 2024-06-06 Xiaoyu Zhang , Matthew Chang , Pranav Kumar , Saurabh Gupta

Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the…

Machine Learning · Computer Science 2019-06-20 Paul Budnarain , Renato Ferreira Pinto Junior , Ilan Kogan

One way to approach end-to-end autonomous driving is to learn a policy function that maps from a sensory input, such as an image frame from a front-facing camera, to a driving action, by imitating an expert driver, or a reference policy.…

Machine Learning · Computer Science 2016-05-23 Jiakai Zhang , Kyunghyun Cho

Deep neural networks trained on demonstrations of human actions give robot the ability to perform self-driving on the road. However, navigation in a pedestrian-rich environment, such as a campus setup, is still challenging---one needs to…

Computer Vision and Pattern Recognition · Computer Science 2018-11-02 Jing Bi , Tianyou Xiao , Qiuyue Sun , Chenliang Xu

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically,…

Machine Learning · Computer Science 2025-04-15 Emilien Biré , Anthony Kobanda , Ludovic Denoyer , Rémy Portelas

The success of automated driving deployment is highly depending on the ability to develop an efficient and safe driving policy. The problem is well formulated under the framework of optimal control as a cost optimization problem. Model…

Artificial Intelligence · Computer Science 2017-06-14 Ahmad El Sallab , Mahmoud Saeed , Omar Abdel Tawab , Mohammed Abdou

The objective of this paper is to develop a sample efficient end-to-end deep learning method for self-driving cars, where we attempt to increase the value of the information extracted from samples, through careful analysis obtained from…

Robotics · Computer Science 2020-07-30 Yunus Bicer , Ali Alizadeh , Nazim Kemal Ure , Ahmetcan Erdogan , Orkun Kizilirmak

Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during policy learning, such as a human performing a novel task or an…

Machine Learning · Computer Science 2020-05-19 Ashwin Balakrishna , Brijen Thananjeyan , Jonathan Lee , Felix Li , Arsh Zahed , Joseph E. Gonzalez , Ken Goldberg

Generalist robot policies that can perform many tasks typically require extensive expert data or simulations for training. In this work, we propose a novel Data-Efficient multitask DAgger framework that distills a single multitask policy…

Machine Learning · Computer Science 2025-10-01 Haotian Fu , Ran Gong , Xiaohan Zhang , Maria Vittoria Minniti , Jigarkumar Patel , Karl Schmeckpeper

Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly employ expert-agent switching systems to reduce the expert's burden by limitedly selecting the…

Robotics · Computer Science 2026-04-23 Taisuke Kobayashi

Imitation learning (IL) provides a data-driven framework for approximating policies for large-scale combinatorial optimisation problems formulated as sequential decision problems (SDPs), where exact solution methods are computationally…

Machine Learning · Computer Science 2026-04-13 Prakash Gawas , Antoine Legrain , Louis-Martin Rousseau
‹ Prev 1 2 3 10 Next ›