English
Related papers

Related papers: Utilizing Skipped Frames in Action Repeats via Pse…

200 papers

Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it. Traditionally, such…

Machine Learning · Computer Science 2020-09-23 Sahil Sharma , Aravind Srinivas , Balaraman Ravindran

Deep reinforcement learning (RL) has gained widespread adoption in recent years but faces significant challenges, particularly in unknown and complex environments. Among these, high-dimensional action selection stands out as a critical…

Machine Learning · Statistics 2025-07-08 Wenbo Zhang , Hengrui Cai

This work aims to learn how to perform complex robot manipulation tasks that are composed of several, consecutively executed low-level sub-tasks, given as input a few visual demonstrations of the tasks performed by a person. The sub-tasks…

Robotics · Computer Science 2022-03-09 Junchi Liang , Bowen Wen , Kostas Bekris , Abdeslam Boularias

Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The…

Machine Learning · Computer Science 2019-05-14 Craig J. Bester , Steven D. James , George D. Konidaris

Machine learning in medical imaging during clinical routine is impaired by changes in scanner protocols, hardware, or policies resulting in a heterogeneous set of acquisition settings. When training a deep learning model on an initial…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Matthias Perkonigg , Johannes Hofmanninger , Christian Herold , Helmut Prosch , Georg Langs

This paper addresses unsupervised action segmentation. Prior work captures the frame-level temporal structure of videos by a feature embedding that encodes time locations of frames in the video. We advance prior work with a new…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Jun Li , Sinisa Todorovic

End-to-end learning is emerging as a powerful paradigm for robotic manipulation, but its effectiveness is limited by data scarcity and the heterogeneity of action spaces across robot embodiments. In particular, diverse action spaces across…

Robotics · Computer Science 2026-03-23 Erik Bauer , Elvis Nava , Robert K. Katzschmann

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

Machine Learning · Computer Science 2019-06-12 Nicholas Ketz , Soheil Kolouri , Praveen Pilly

Policy Dual Averaging (PDA) offers a principled Policy Mirror Descent (PMD) framework that more naturally admits value function approximation than standard PMD, enabling the use of approximate advantage (or Q-) functions while retaining…

Machine Learning · Computer Science 2026-03-12 Ji Gao , Caleb Ju , Guanghui Lan , Zhaohui Tong

Deep Reinforcement Learning methods have achieved state of the art performance in learning control policies for the games in the Atari 2600 domain. One of the important parameters in the Arcade Learning Environment (ALE) is the frame skip…

Machine Learning · Computer Science 2020-09-23 Aravind Srinivas , Sahil Sharma , Balaraman Ravindran

Learning actions that are relevant to decision-making and can be executed effectively is a key problem in autonomous robotics. Current state-of-the-art action representations in robotics lack proper effect-driven learning of the robot's…

Robotics · Computer Science 2024-04-04 Marko Zaric , Jakob Hollenstein , Justus Piater , Erwan Renaudo

Deep Neural networks forget previously learnt tasks when they are faced with learning new tasks. This is called catastrophic forgetting. Rehearsing the neural network with the training data of the previous task can protect the network from…

Machine Learning · Computer Science 2020-04-29 Bhasker Sri Harsha Suri , Kalidas Yeturu

In order perform a large variety of tasks and to achieve human-level performance in complex real-world environments, Artificial Intelligence (AI) Agents must be able to learn from their past experiences and gain both knowledge and an…

Machine Learning · Computer Science 2019-05-13 Andrei Claudiu Roibu

The growing demands of stroke rehabilitation have increased the need for solutions to support autonomous exercising. Virtual coaches can provide real-time exercise feedback from video data, helping patients improve motor function and keep…

Image and Video Processing · Electrical Eng. & Systems 2025-06-05 Gonçalo Mesquita , Ana Rita Cóias , Artur Dubrawski , Alexandre Bernardino

Sensing technology has significantly advanced in automating systems that reflect human movement, particularly in robotics and healthcare, where it is used to automatically detect target movements. This study develops a method to…

Machine Learning · Computer Science 2024-10-10 Yooseok Lim , Sujee Lee

The task of action recognition has been in the forefront of research, given its applications in gaming, surveillance and health care. In this work, we propose a simple, yet very effective approach which works seamlessly for both offline and…

Computer Vision and Pattern Recognition · Computer Science 2016-11-02 Yashas Annadani , D L Rakshith , Soma Biswas

Action segmentation of behavioral videos is the process of labeling each frame as belonging to one or more discrete classes, and is a crucial component of many studies that investigate animal behavior. A wide range of algorithms exist to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Ari Blau , Evan S Schaffer , Neeli Mishra , Nathaniel J Miska , The International Brain Laboratory , Liam Paninski , Matthew R Whiteway

When enough annotated training data is available, supervised deep-learning algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Andrey Davydov , Alexey Sidnev , Artsiom Sanakoyeu , Yuhua Chen , Mathieu Salzmann , Pascal Fua

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Computer Vision and Pattern Recognition · Computer Science 2019-02-21 Xiao-Yu Zhang , Haichao Shi , Changsheng Li , Kai Zheng , Xiaobin Zhu , Lixin Duan

We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn…

Graphics · Computer Science 2023-05-08 Pei Xu , Xiumin Shang , Victor Zordan , Ioannis Karamouzas