TY - JOUR
T1 - Heuristically Accelerated Reinforcement Learning by Means of Case-Based Reasoning and Transfer Learning
AU - Bianchi, Reinaldo A.C.
AU - Santos, Paulo E.
AU - da Silva, Isaac J.
AU - Celiberto, Luiz A.
AU - Lopez de Mantaras, Ramon
PY - 2018/8
Y1 - 2018/8
N2 - 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.
AB - 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.
KW - Case-based reasoning
KW - Reinforcement learning
KW - Robotics
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85032696272&partnerID=8YFLogxK
U2 - 10.1007/s10846-017-0731-2
DO - 10.1007/s10846-017-0731-2
M3 - Article
AN - SCOPUS:85032696272
SN - 0921-0296
VL - 91
SP - 301
EP - 312
JO - Journal of Intelligent and Robotic Systems: Theory and Applications
JF - Journal of Intelligent and Robotic Systems: Theory and Applications
IS - 2
ER -