Multi-Agent Reinforcement Learning (MARL) algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning …
Performing reinforcement learning-based control of systems whose state space has many Undesired Terminal States (UTS) experiences severe convergence problems. We define …
JM Lopez‐Guede, B Fernandez‐Gauna… - Computational …, 2015 - Wiley Online Library
Multiagent systems are increasingly present in computational environments. However, the problem of agent design or control is an open research field. Reinforcement learning …
JM Lopez-Guede, B Fernandez-Gauna… - Neurocomputing, 2015 - Elsevier
Autonomous task learning for Linked Multicomponent Robotic Systems (L-MCRS) is an open research issue. Pilot studies applying Reinforcement Learning (RL) on Single Robot …
W Wang, S Li, H Qin, A Hao - 2015 14th International …, 2015 - ieeexplore.ieee.org
Despite the long R&D history of interactive minimally-invasive surgery and therapy simulations, the guide wire/catheter behavior modeling remains challenging in …
JM Lopez-Guede, J Estévez, M Graña - 10th International Conference on …, 2015 - Springer
In this paper we address the physical realization of proof of concept experiments demonstrating the suitability of the controllers learned by means of Reinforcement Learning …
Improvements in quality and safety standards in surgical training, reduction in training hours and constant technological advances have challenged the traditional apprenticeship model …