English
Related papers

Related papers: Learning Parameterized Skills

200 papers

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between…

Machine Learning · Computer Science 2022-10-24 Lingfeng Sun , Haichao Zhang , Wei Xu , Masayoshi Tomizuka

Designing a multi-layer optical system with designated optical characteristics is an inverse design problem in which the resulting design is determined by several discrete and continuous parameters. In particular, we consider three design…

Machine Learning · Computer Science 2021-11-17 Heribert Wankerl , Maike L. Stern , Ali Mahdavi , Christoph Eichler , Elmar W. Lang

The recently introduced path-star task is a minimal task designed to exemplify limitations to the abilities of language models (Bachmann and Nagarajan, 2024). It involves a path-star graph where multiple arms radiate from a single starting…

Computation and Language · Computer Science 2025-05-21 Arvid Frydenlund

Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first…

Robotics · Computer Science 2024-05-10 Shih-Min Yang , Martin Magnusson , Johannes A. Stork , Todor Stoyanov

Analyzing large volumes of high-dimensional data requires dimensionality reduction: finding meaningful low-dimensional structures hidden in their high-dimensional observations. Such practice is needed in atomistic simulations of complex…

Computational Physics · Physics 2023-10-17 Jakub Rydzewski , Ming Chen , Omar Valsson

Traditionally, graph neural networks have been trained using a single observed graph. However, the observed graph represents only one possible realization. In many applications, the graph may encounter uncertainties, such as having…

Machine Learning · Computer Science 2024-10-10 See Hian Lee , Feng Ji , Kelin Xia , Wee Peng Tay

A procedure for unfolding the true distribution from experimental data is presented. Machine learning methods are applied for simultaneous identification of an apparatus function and solving of an inverse problem. A priori information about…

Data Analysis, Statistics and Probability · Physics 2011-05-26 Nikolai Gagunashvili

Analyzing signals arising from dynamical systems typically requires many modeling assumptions and parameter estimation. In high dimensions, this modeling is particularly difficult due to the "curse of dimensionality". In this paper, we…

Systems and Control · Computer Science 2016-12-21 Tal Shnitzer , Ronen Talmon , Jean-Jacques Slotine

This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch between skills automatically and naturally in tracking…

Machine learning requires exuberant amounts of data and computation. Also, models require equally excessive growth in the number of parameters. It is, therefore, sensible to look for technologies that reduce these demands on resources.…

Machine Learning · Computer Science 2023-03-29 Danko Nikolić , Davor Andrić , Vjekoslav Nikolić

Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…

Machine Learning · Computer Science 2016-09-23 Coline Devin , Abhishek Gupta , Trevor Darrell , Pieter Abbeel , Sergey Levine

Learning from Demonstration (LfD) enables robots to acquire versatile skills by learning motion policies from human demonstrations. It endows users with an intuitive interface to transfer new skills to robots without the need for…

Robotics · Computer Science 2023-10-27 Jianyong Sun , Jens Kober , Michael Gienger , Jihong Zhu

We present Skill Transformer, an approach for solving long-horizon robotic tasks by combining conditional sequence modeling and skill modularity. Conditioned on egocentric and proprioceptive observations of a robot, Skill Transformer is…

Machine Learning · Computer Science 2023-08-22 Xiaoyu Huang , Dhruv Batra , Akshara Rai , Andrew Szot

Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a…

Machine Learning · Computer Science 2020-05-15 Alexander C. Li , Carlos Florensa , Ignasi Clavera , Pieter Abbeel

In a sequential decision-making problem, having a structural dependency amongst the reward distributions associated with the arms makes it challenging to identify a subset of alternatives that guarantees the optimal collective outcome.…

Machine Learning · Computer Science 2022-12-27 Behzad Nourani-Koliji , Saeed Ghoorchian , Setareh Maghsudi

Our goal is to provide a review of deep learning methods which provide insight into structured high-dimensional data. Rather than using shallow additive architectures common to most statistical models, deep learning uses layers of…

Machine Learning · Statistics 2023-10-11 Nick Polson , Vadim Sokolov

A protocol for distributed estimation of discrete distributions is proposed. Each agent begins with a single sample from the distribution, and the goal is to learn the empirical distribution of the samples. The protocol is based on a simple…

Optimization and Control · Mathematics 2014-06-06 Anand D. Sarwate , Tara Javidi

The process of learning a manipulation task depends strongly on the action space used for exploration: posed in the incorrect action space, solving a task with reinforcement learning can be drastically inefficient. Additionally, similar…

In recent years, Reinforcement Learning (RL) is becoming a popular technique for training controllers for robots. However, for complex dynamic robot control tasks, RL-based method often produces controllers with unrealistic styles. In…

Robotics · Computer Science 2023-09-19 Xiang Zhu , Zixuan Chen , Jianyu Chen

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations,…