Combining reinforcement learning with symbolic planning

TY - GEN

T1 - Combining reinforcement learning with symbolic planning

AU - Grounds, Matthew

AU - Kudenko, Daniel

PY - 2008

Y1 - 2008

N2 - One of the major difficulties in applying Q-learning to real-world domains is the sharp increase in the number of learning steps required to converge towards an optimal policy as the size of the state space is increased. In this paper we propose a method, PLANQ-learning, that couples a Q-learner with a STRIPS planner. The planner shapes the reward function, and thus guides the Q-learner quickly to the optimal policy. We demonstrate empirically that this combination of high-level reasoning and low-level learning displays significant improvements in scaling-up behaviour as the state-space grows larger, compared to both standard Q-learning and hierarchical Q-learning methods.

AB - One of the major difficulties in applying Q-learning to real-world domains is the sharp increase in the number of learning steps required to converge towards an optimal policy as the size of the state space is increased. In this paper we propose a method, PLANQ-learning, that couples a Q-learner with a STRIPS planner. The planner shapes the reward function, and thus guides the Q-learner quickly to the optimal policy. We demonstrate empirically that this combination of high-level reasoning and low-level learning displays significant improvements in scaling-up behaviour as the state-space grows larger, compared to both standard Q-learning and hierarchical Q-learning methods.

UR - http://www.scopus.com/inward/record.url?scp=49949114782&partnerID=8YFLogxK

M3 - Conference contribution

SN - 978-3-540-77947-6

VL - 4865 LNAI

SP - 75

EP - 86

BT - ADAPTIVE AGENTS AND MULTI-AGENT SYSTEMS

A2 - Tuyls, K

A2 - Nowe, A

A2 - Guessoum, Z

A2 - Kudenko, D

PB - Springer

CY - BERLIN

ER -