English
Related papers

Related papers: TRAIL: Near-Optimal Imitation Learning with Subopt…

200 papers

Inspired by how humans combine direct interaction with action-free experience (e.g., videos), we study world models that learn from heterogeneous data. Standard world models typically rely on action-conditioned trajectories, which limits…

Machine Learning · Computer Science 2025-12-12 Marvin Alles , Xingyuan Zhang , Patrick van der Smagt , Philip Becker-Ehmck

Natural agents can effectively learn from multiple data sources that differ in size, quality, and types of measurements. We study this heterogeneity in the context of offline reinforcement learning (RL) by introducing a new, practically…

Machine Learning · Computer Science 2023-06-23 Qinqing Zheng , Mikael Henaff , Brandon Amos , Aditya Grover

Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. Some SSIL methods learn an inverse dynamics model (IDM) to…

Machine Learning · Computer Science 2026-02-04 Sacha Morin , Moonsub Byeon , Alexia Jolicoeur-Martineau , Sébastien Lachapelle

Growing demands in today's industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional…

Systems and Control · Electrical Eng. & Systems 2023-03-28 Anantha Sai Hariharan Vinjarapu , Yorick Broens , Hans Butler , Roland Tóth

Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…

Robotics · Computer Science 2026-05-20 Dongjie Yu , Kun Lei , Zhennan Jiang , Jia Pan , Huazhe Xu

Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised,…

Machine Learning · Computer Science 2026-02-12 Li-Min Chu , Kai-Siang Ma , Ming-Hong Chen , Ping-Chun Hsieh

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…

Robotics · Computer Science 2022-11-02 Mingxi Jia , Dian Wang , Guanang Su , David Klee , Xupeng Zhu , Robin Walters , Robert Platt

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Robotics · Computer Science 2025-05-07 Sachit Kuhar , Shuo Cheng , Shivang Chopra , Matthew Bronars , Danfei Xu

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…

Artificial Intelligence · Computer Science 2024-06-10 Federico Malato , Ville Hautamaki

Data is often generated in streams, with new observations arriving over time. A key challenge for learning models from data streams is capturing relevant information while keeping computational costs manageable. We explore intelligent data…

Machine Learning · Computer Science 2025-12-23 Benedetta Lavinia Mussati , Freddie Bickford Smith , Tom Rainforth , Stephen Roberts

Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose"…

Machine Learning · Computer Science 2026-02-17 Stefano Woerner , Seong Joon Oh , Christian F. Baumgartner

Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of…

Machine Learning · Computer Science 2018-12-03 Adrian Šošić , Elmar Rueckert , Jan Peters , Abdelhak M. Zoubir , Heinz Koeppl

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main categories of methods are used:…

Machine Learning · Computer Science 2023-07-04 Paria Rashidinejad , Banghua Zhu , Cong Ma , Jiantao Jiao , Stuart Russell

Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots. However, real-world applications often require a specialized suite of skills…

Computation and Language · Computer Science 2024-06-14 Mengzhou Xia , Sadhika Malladi , Suchin Gururangan , Sanjeev Arora , Danqi Chen

Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such…

The use of imitation learning to learn a single policy for a complex task that has multiple modes or hierarchical structure can be challenging. In fact, previous work has shown that when the modes are known, learning separate policies for…

Machine Learning · Computer Science 2019-03-13 Arjun Sharma , Mohit Sharma , Nicholas Rhinehart , Kris M. Kitani

In the search for more sample-efficient reinforcement-learning (RL) algorithms, a promising direction is to leverage as much external off-policy data as possible. For instance, expert demonstrations. In the past, multiple ideas have been…

Machine Learning · Computer Science 2023-03-01 Jesus Bujalance Martin , Fabien Moutarde

Dynamic quadruped locomotion over challenging terrains with precise foot placements is a hard problem for both optimal control methods and Reinforcement Learning (RL). Non-linear solvers can produce coordinated constraint satisfying…

Robotics · Computer Science 2021-11-02 Philemon Brakel , Steven Bohez , Leonard Hasenclever , Nicolas Heess , Konstantinos Bousmalis

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…

Machine Learning · Computer Science 2022-05-24 Hana Hoshino , Kei Ota , Asako Kanezaki , Rio Yokota

We propose and analyze TRAiL (Tangential Randomization in Linear Bandits), a computationally efficient regret-optimal forced exploration algorithm for linear bandits on action sets that are sublevel sets of strongly convex functions. TRAiL…

Machine Learning · Statistics 2024-11-20 Arda Güçlü , Subhonmesh Bose