20182020

Research output per year

If you made any changes in Pure these will be visible here soon.

Research Output

  • 3 Conference contribution
  • 3 Article
2020

Interactive Learning of Temporal Features for Control: Shaping Policies and State Representations From Human Feedback

Perez-Dattari, R., Celemin, C., Franzese, G., Ruiz-del-Solar, J. & Kober, J., 2020, In : IEEE Robotics and Automation Magazine. 27, 2, p. 46-54

Research output: Contribution to journalArticleScientificpeer-review

Open Access
File
50 Downloads (Pure)

Interactive Learning with Corrective Feedback for Policies Based on Deep Neural Networks

Perez Dattari, R., Celemin, C., Ruiz-del-Solar, J. & Kober, J., 2020, Proceedings of the 2018 International Symposium on Experimental Robotics. Xiao, J., Kröger, T. & Khatib, O. (eds.). Cham, Switzerland: Springer, p. 353-363 (Springer Proceedings in Advanced Robotics; vol. 11).

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2019

Continuous control for high-dimensional state spaces: An interactive learning approach

Pérez-Dattari, R., Celemin, C., Ruiz-Del-Solar, J. & Kober, J., 1 May 2019, 2019 International Conference on Robotics and Automation, ICRA 2019. Institute of Electrical and Electronics Engineers (IEEE), Vol. 2019-May. p. 7611-7617 7 p. 8793675

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)

Reinforcement learning of motor skills using Policy Search and human corrective advice

Celemin, C., Maeda, G., Ruiz-del-Solar, J., Peters, J. & Kober, J., 2019, In : International Journal of Robotics Research. 38, 14, p. 1560-1580

Research output: Contribution to journalArticleScientificpeer-review

Open Access
File
1 Citation (Scopus)
134 Downloads (Pure)

Simultaneous learning of objective function and policy from interactive teaching with corrective feedback

Celemin, C. & Kober, J., 2019, Proceedings of the 2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2019. Piscataway, NJ, USA: IEEE, p. 726-732

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Open Access
File
42 Downloads (Pure)
2018

A fast hybrid reinforcement learning framework with human corrective feedback

Celemin, C., Ruiz-del-Solar, J. & Kober, J., 2018, In : Autonomous Robots. 43 (2019), 5, p. 1173-1186

Research output: Contribution to journalArticleScientificpeer-review

Open Access
File
8 Citations (Scopus)
50 Downloads (Pure)