English
Related papers

Related papers: Not Only Domain Randomization: Universal Policy wi…

200 papers

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of…

Artificial Intelligence · Computer Science 2023-10-26 Michael Beukman , Devon Jarvis , Richard Klein , Steven James , Benjamin Rosman

Recent work has shown results on learning navigation policies for idealized cylinder agents in simulation and transferring them to real wheeled robots. Deploying such navigation policies on legged robots can be challenging due to their…

Robotics · Computer Science 2021-09-14 Joanne Truong , Denis Yarats , Tianyu Li , Franziska Meier , Sonia Chernova , Dhruv Batra , Akshara Rai

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

Robotics · Computer Science 2022-05-10 Hirotaka Tahara , Hikaru Sasaki , Hanbit Oh , Brendan Michael , Takamitsu Matsubara

We study the problem of Safe Policy Improvement (SPI) under constraints in the offline Reinforcement Learning (RL) setting. We consider the scenario where: (i) we have a dataset collected under a known baseline policy, (ii) multiple reward…

Machine Learning · Computer Science 2021-11-01 Harsh Satija , Philip S. Thomas , Joelle Pineau , Romain Laroche

This article presents a constrained policy optimization approach for the optimal control of systems under nonstationary uncertainties. We introduce an assumption that we call Markov embeddability that allows us to cast the stochastic…

Optimization and Control · Mathematics 2026-05-11 Sungho Shin , François Pacaud , Emil Contantinescu , Mihai Anitescu

We introduce an algorithm for tackling the problem of unsupervised domain adaptation (UDA) in continual learning (CL) scenarios. The primary objective is to maintain model generalization under domain shift when new domains arrive…

Machine Learning · Computer Science 2024-02-02 Mohammad Rostami

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a…

One of the main challenges in the field of embodied artificial intelligence is the open-ended autonomous learning of complex behaviours. Our approach is to use task-independent, information-driven intrinsic motivation(s) to support…

Artificial Intelligence · Computer Science 2013-09-27 Keyan Zahedi , Georg Martius , Nihat Ay

Sampling-based motion planners have experienced much success due to their ability to efficiently and evenly explore the state space. However, for many tasks, it may be more efficient to not uniformly explore the state space, especially when…

Robotics · Computer Science 2018-06-07 Clark Zhang , Jinwook Huh , Daniel D. Lee

Many deep reinforcement learning algorithms contain inductive biases that sculpt the agent's objective and its interface to the environment. These inductive biases can take many forms, including domain knowledge and pretuned…

Machine Learning · Computer Science 2019-07-08 Matteo Hessel , Hado van Hasselt , Joseph Modayil , David Silver

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-task learning at a cost…

Machine Learning · Computer Science 2020-11-24 Elahe Aghapour , Nora Ayanian

Prediction models frequently face the challenge of concept drift, in which the underlying data distribution changes over time, weakening performance. Examples can include models which predict loan default, or those used in healthcare…

Machine Learning · Computer Science 2024-12-16 Louis Chislett , Catalina A. Vallejos , Timothy I. Cannings , James Liley

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most…

Machine Learning · Computer Science 2022-03-15 Xiaoyu Chen , Jiachen Hu , Chi Jin , Lihong Li , Liwei Wang

Controlling stochastic systems with unknown dynamics and under complex specifications is specially challenging in safety-critical settings, where performance guarantees are essential. We propose a data-driven policy synthesis framework that…

Systems and Control · Electrical Eng. & Systems 2025-12-17 Ibon Gracia , Morteza Lahijanian

Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s)…

Machine Learning · Computer Science 2022-10-25 Jean-Baptiste Gaya , Laure Soulier , Ludovic Denoyer

Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to…

Computer Vision and Pattern Recognition · Computer Science 2020-02-28 Yichun Shi , Xiang Yu , Kihyuk Sohn , Manmohan Chandraker , Anil K. Jain

Dynamic platforms that operate over many unique terrain conditions typically require many behaviours. To transition safely, there must be an overlap of states between adjacent controllers. We develop a novel method for training setup…

Robotics · Computer Science 2022-10-07 Brendan Tidd , Nicolas Hudson , Akansel Cosgun , Jurgen Leitner

Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and…

Machine Learning · Computer Science 2018-09-17 Isac Arnekvist , Danica Kragic , Johannes A. Stork

Mainstream visuomotor policies predominantly rely on generative models for holistic action prediction, while current autoregressive policies, predicting the next token or chunk, have shown suboptimal results. This motivates a search for…

Robotics · Computer Science 2025-03-18 Yue Su , Xinyu Zhan , Hongjie Fang , Han Xue , Hao-Shu Fang , Yong-Lu Li , Cewu Lu , Lixin Yang