A Comparative Study of Reinforcement Learning Mechanisms for Robot Online Adaptation under Progressive Damage
Abstract
Visual representation of the application of a 7-sensor epsilon-greedy mechanism to avoid obstacles with Thymio. The first video recording was taken with all working sensors. Afterwards, we manually deactivated one of the sensors to simulate a damaged state of the Thymio and recorded its recovery from epochs 5 to 250.
Fields of Study & Subjects
Reinforcement Learning in Robotics
Modular Robots and Swarm Intelligence
Educational Robotics and Engineering
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 3 March 2026
- Language
- EN