Learning unsupervised disentangled skill latents to adapt unseen task and morphological modifications
Authors:
- Taewoo KimTKTaewoo Kim
- Pamul YadavPYPamul Yadav
- Ho SukHSHo Suk
- Shiho KimSKShiho Kim
Open Access
- 5 September 2022
- journal article
- research article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 116
Abstract
No abstract availableKeywords
Funding Information
- Ministry of Science, ICT and Future Planning (2020-0-00056)
- Institute for Information and Communications Technology Promotion (2022-0-00966)
This publication has 9 references indexed in Scilit:
- Policy Iteration Reinforcement Learning-based control using a Grey Wolf Optimizer algorithmInformation Sciences, 2022
- Overcoming model bias for robust offline deep reinforcement learningEngineering Applications of Artificial Intelligence, 2021
- IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Real-world embodied AI through a morphologically adaptive quadruped robotNature Machine Intelligence, 2021
- Interpretable policies for reinforcement learning by genetic programmingEngineering Applications of Artificial Intelligence, 2018
- Robots that can adapt like animalsNature, 2015
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Synaptic plasticity: taming the beastNature Neuroscience, 2000
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951