Title | ||
---|---|---|
Heuristically Accelerated Reinforcement Learning by Means of Case-Based Reasoning and Transfer Learning |
Abstract | ||
---|---|---|
Reinforcement Learning (RL) is a well-known technique for learning the solutions of control problems from the interactions of an agent in its domain. However, RL is known to be inefficient in problems of the real-world where the state space and the set of actions grow up fast. Recently, heuristics, case-based reasoning (CBR) and transfer learning have been used as tools to accelerate the RL process. This paper investigates a class of algorithms called Transfer Learning Heuristically Accelerated Reinforcement Learning (TLHARL) that uses CBR as heuristics within a transfer learning setting to accelerate RL. The main contributions of this work are the proposal of a new TLHARL algorithm based on the traditional RL algorithm () and the application of TLHARL on two distinct real-robot domains: a robot soccer with small-scale robots and the humanoid-robot stability learning. Experimental results show that our proposed method led to a significant improvement of the learning rate in both domains. |
Year | DOI | Venue |
---|---|---|
2018 | https://doi.org/10.1007/s10846-017-0731-2 | Journal of Intelligent and Robotic Systems |
Keywords | Field | DocType |
Reinforcement learning,Transfer learning,Case-based reasoning,Robotics,07.05.Mh | Heuristic,Transfer of learning,Heuristics,Artificial intelligence,Engineering,Robot,Case-based reasoning,State space,Machine learning,Learning classifier system,Reinforcement learning | Journal |
Volume | Issue | ISSN |
91 | 2 | 0921-0296 |
Citations | PageRank | References |
4 | 0.37 | 25 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Reinaldo A. C. Bianchi | 1 | 147 | 17.63 |
Paulo E. Santos | 2 | 131 | 20.29 |
Isaac J. da Silva | 3 | 4 | 0.37 |
Luiz A. Celiberto, Jr. | 4 | 18 | 2.32 |
Ramon Lopez de Mantaras | 5 | 706 | 52.40 |