caa a22 4500 606159908 CHVBK 20210128100627.0 cr unu---uuuuu 210128e20151101xx s 000 0 eng 10.1007/s00521-015-1861-8 doi (NATIONALLICENCE)springer-10.1007/s00521-015-1861-8 Topological Q-learning with internally guided exploration for mobile robot navigation [Elektronische Daten] [Muhammad Hafez, Chu Loo] Improving the learning convergence of reinforcement learning (RL) in mobile robot navigation has been the interest of many recent works that have investigated different approaches to obtain knowledge from effectively and efficiently exploring the robot's environment. In RL, this knowledge is of great importance for reducing the high number of interactions required for updating the value function and to eventually find an optimal or a nearly optimal policy for the agent. In this paper, we propose a topological Q-learning (TQ-learning) algorithm that makes use of the topological ordering among the observed states of the environment in which the agent acts. This algorithm builds an incremental topological map of the environment using Instantaneous Topological Map model which we use for accelerating value function updates as well as providing a guided exploration strategy for the agent. We evaluate our algorithm against the original Q-learning and the Influence Zone algorithms in static and dynamic environments. The Natural Computing Applications Forum, 2015 Reinforcement learning nationallicence Q-learning nationallicence Convergence acceleration nationallicence Topological map nationallicence Guided exploration nationallicence Hafez Muhammad Faculty of Computer Science and Information Technology, University of Malaya, 50603, Kuala Lumpur, Malaysia aut Loo Chu Faculty of Computer Science and Information Technology, University of Malaya, 50603, Kuala Lumpur, Malaysia aut Neural Computing and Applications Springer London 26/8(2015-11-01), 1939-1954 0941-0643 26:8<1939 2015 26 521 https://doi.org/10.1007/s00521-015-1861-8 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-015-1861-8 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Hafez Muhammad Faculty of Computer Science and Information Technology, University of Malaya, 50603, Kuala Lumpur, Malaysia aut NATIONALLICENCE 700 1- Loo Chu Faculty of Computer Science and Information Technology, University of Malaya, 50603, Kuala Lumpur, Malaysia aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/8(2015-11-01), 1939-1954 0941-0643 26:8<1939 2015 26 521