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 Q(λ) 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.
Original language | English |
---|---|
Pages (from-to) | 301-312 |
Number of pages | 12 |
Journal | Journal of Intelligent and Robotic Systems: Theory and Applications |
Volume | 91 |
Issue number | 2 |
Early online date | 30 Oct 2017 |
DOIs | |
Publication status | Published - Aug 2018 |
Externally published | Yes |
Keywords
- Case-based reasoning
- Reinforcement learning
- Robotics
- Transfer learning