Christos Spatharis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Christos Spatharis has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Konstantinos Blekas
Department of Computer Science and Engineering, University of Ioannina, Ioannina, Greece
3 shared publications - Piyabhum Chaysri
Department of Computer Science and Engineering, University of Ioannina, Ioannina, Greece
2 shared publications - Theodore Tranos
Department of Computer Science and Engineering, Polytechnic School, University of Ioannina, 45110 Ioannina, Greece
2 shared publications - Dimitrios Koutrintzes
National Centre for Scientific Research ‘Demokritos’, Ag. Paraskevi, Greece
1 shared publication - George A. Vouros
Department of Digital Systems, University of Piraeus, 185 34 Piraeus, Greece
1 shared publication - Maria Dagioglou
National Centre for Scientific Research ‘Demokritos’, Ag. Paraskevi, Greece
1 shared publication
Latest Publications
- 17 April 2026
- Published by Elsevier in Ocean Engineering
- Vol. 357
A multi-task reinforcement learning framework for resilient autonomous USV navigation
- 17 April 2026
- Published by Elsevier in Ocean Engineering
- Vol. 357
A multi-task reinforcement learning framework for resilient autonomous USV navigation
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 773-777
First Impressions Matter: Primacy Bias in Deep Reinforcement Learning during Human-Robot Co-learning
Deep reinforcement learning enables robots to learn collaborative tasks with humans. However, off-policy methods suffer from primacy bias that causes agents to overfit to early experiences. We investigate the impact of primacy bias on team performance during a real world human-robot co-learning task, where twenty novice human participants collaborated with a Soft Actor-Critic agent to move a UR3 cobot. Analysis of how initial interactions shape subsequent learning dynamics demonstrates that the quality of the initial data distribution matters. While successful early experiences allow teams to overcome learning barriers, poor interactions cause the agent to converge toward suboptimal behaviors that prevent recovery, even as human skills improve.
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 773-777
Open AccessFirst Impressions Matter: Primacy Bias in Deep Reinforcement Learning during Human-Robot Co-learning
Deep reinforcement learning enables robots to learn collaborative tasks with humans. However, off-policy methods suffer from primacy bias that causes agents to overfit to early experiences. We investigate the impact of primacy bias on team performance during a real world human-robot co-learning task, where twenty novice human participants collaborated with a Soft Actor-Critic agent to move a UR3 cobot. Analysis of how initial interactions shape subsequent learning dynamics demonstrates that the quality of the initial data distribution matters. While successful early experiences allow teams to overcome learning barriers, poor interactions cause the agent to converge toward suboptimal behaviors that prevent recovery, even as human skills improve.
- Open Access
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
An Advanced Deep Reinforcement Learning Framework for Docking Unmanned Surface Vessels in Variable Environmental Conditions and Amid Moving Ships
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessAn Advanced Deep Reinforcement Learning Framework for Docking Unmanned Surface Vessels in Variable Environmental Conditions and Amid Moving Ships
- 3 June 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (11-12) , 7118-7134
Modelling flight trajectories with multi-modal generative adversarial imitation learning
- 3 June 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (11-12) , 7118-7134
Modelling flight trajectories with multi-modal generative adversarial imitation learning