Results 41 to 50 of about 96,046 (256)

Learning Sequential Force Interaction Skills

Robotics, 2020
Learning skills from kinesthetic demonstrations is a promising way of minimizing the gap between human manipulation abilities and those of robots. We propose an approach to learn sequential force interaction skills from such demonstrations.
Simon Manschitz, Michael Gienger, Jens Kober, Jan Peters   +3 more
doaj   +1 more source

MODEL-FREE LEARNING FROM DEMONSTRATION

Proceedings of the 2nd International Conference on Agents and Artificial Intelligence, 2010
A novel robot learning algorithm called Predictive Sequence Learning (PSL) is presented and evaluated.
Billing, Erik, Hellström, Thomas, Janlert, Lars Erik   +2 more
openaire   +4 more sources

State Representation Learning from Demonstration [PDF]

, 2020
Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact representation of such a state is beneficial to help robots grasp onto their environment for interacting. The properties of
Merckling, Astrid, Coninx, Alexandre, Cressot, Loic, Doncieux, Stephane, Perrin, Nicolas   +4 more
openaire   +3 more sources

Learning tasks from a single demonstration [PDF]

Proceedings of International Conference on Robotics and Automation, 2002
Learning a complex dynamic robot manoeuvre from a single human demonstration is difficult. This paper explores an approach to learning from demonstration based on learning an optimization criterion from the demonstration and a task model from repeated attempts to perform the task, and using the learned criterion and model to compute an appropriate ...
Christopher G. Atkeson, Stefan Schaal
openaire   +1 more source

A Biologically Inspired Program-Level Imitation Approach for Robots

IEEE Access
Robots may learn new skills from humans to better assist us with everyday tasks. We propose a novel, biologically inspired imitation approach to enable robots to understand and perform complex actions using high-level programs that incorporate sequential
Pourya Aliasghari, Moojan Ghafurian, Chrystopher L. Nehaniv, Kerstin Dautenhahn   +3 more
doaj   +1 more source

Guidelines for Pediatric Radiotherapy Simulation: A Report From the Children's Oncology Group Radiation Oncology Discipline

Pediatric Blood &Cancer, EarlyView.
ABSTRACT Pediatric radiation therapy presents unique challenges compared to adult treatments, including those of immobilization, potential need for sedation, and the critical importance of accurate, reproducible positioning. Additionally, heightened attention to imaging doses is necessary to minimize long‐term toxicity in survivors.
Parham Alaei, Stephen Mihalcik, Sujith Baliga, Young Kwok, Dana Casey, Eric Ehler, Christiane Burton, John C. Breneman, Daphne A. Haas‐Kogan, Suzanne L. Wolden, Arnold C. Paulino, Nadia N. Laack, Natia Esiashvili, Sarah Milgrom, Christine Hill‐Kayser, Thomas J. Fitzgerald, John A. Kalapurakal, Chia‐Ho Hua   +17 more
wiley   +1 more source

Neural scalarisation for multi-objective inverse reinforcement learning

SICE Journal of Control, Measurement, and System Integration, 2023
Multi-objective inverse reinforcement learning (MOIRL) extends inverse reinforcement learning (IRL) to multi-objective problems by estimating weights and multi-objective rewards to help retrain and analyse preference-conditioned behaviour.
Daiko Kishikawa, Sachiyo Arai
doaj   +1 more source

Development of Physics Demonstration Videos on Youtube (PDVY) as Physics Learning Media

Jurnal Pendidikan Fisika Indonesia, 2022
The availability of physics demonstration videos relevant to curriculum needs is still limited. The aims of this study were (1) to develop physics learning media in the form of demonstration videos; (2) testing the feasibility of using demonstration ...
A I Irvani, R Warliani
doaj   +1 more source

Deep Q-learning From Demonstrations

Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor.
Todd Hester, Matej Vecerík, Olivier Pietquin, Marc Lanctot, Tom Schaul, Bilal Piot, Dan Horgan, John Quan, Andrew Sendonaris, Ian Osband, Gabriel Dulac-Arnold, John P. Agapiou, Joel Z. Leibo, Audrunas Gruslys   +13 more
openaire   +2 more sources

Robot Learning from Failed Demonstrations [PDF]

International Journal of Social Robotics, 2012
Robot Learning from Demonstration (RLfD) seeks to enable lay users to encode desired robot behaviors as autonomous controllers. Current work uses a human’s demonstration of the target task to initialize the robot’s policy, and then improves its performance either through practice (with a known reward function), or additional human interaction.
Daniel H. Grollman, Aude Billard
openaire   +2 more sources