Proceedings of the 33nd conference on Winter simulation
Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
Representation and timing in theories of the dopamine system
Neural Computation
Application of reinforcement learning to the game of Othello
Computers and Operations Research
Simulation-optimization using a reinforcement learning approach
Proceedings of the 40th Conference on Winter Simulation
Reinforcement Learning: A Tutorial Survey and Recent Advances
INFORMS Journal on Computing
Learning Representation and Control in Markov Decision Processes: New Frontiers
Foundations and Trends® in Machine Learning
A neurocomputational model for cocaine addiction
Neural Computation
An RL-based scheduling algorithm for video traffic in high-rate wireless personal area networks
Computer Networks: The International Journal of Computer and Telecommunications Networking
Learning and adaptation of a policy for dynamic order acceptance in make-to-order manufacturing
Computers and Industrial Engineering
Application of reinforcement learning for agent-based production scheduling
Engineering Applications of Artificial Intelligence
Real-valued Q-learning in multi-agent cooperation
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Approximate dynamic programming for an inventory problem: Empirical comparison
Computers and Industrial Engineering
Computers and Operations Research
Performance bounds for mobile cellular networks with handover prediction
MMNS'05 Proceedings of the 8th international conference on Management of Multimedia Networks and Services
EURO-NGI'05 Proceedings of the Second international conference on Wireless Systems and Network Architectures in Next Generation Internet
Induced states in a decision tree constructed by Q-learning
Information Sciences: an International Journal
| Hi-index | 0.01 |
A large class of problems of sequential decision making under uncertainty, of which the underlying probability structure is a Markov process, can be modeled as stochastic dynamic programs (referred to, in general, as Markov decision problems or MDPs). However, the computational complexity of the classical MDP algorithms, such as value iteration and policy iteration, is prohibitive and can grow intractably with the size of the problem and its related data. Furthermore, these techniques require for each action the one step transition probability and reward matrices, and obtaining these is often unrealistic for large and complex systems. Recently, there has been much interest in a simulation-based stochastic approximation framework called reinforcement learning (RL), for computing near optimal policies for MDPs. RL has been successfully applied to very large problems, such as elevator scheduling, and dynamic channel allocation of cellular telephone systems. In this paper, we extend RL to a more general class of decision tasks that are referred to as semi-Markov decision problems (SMDPs). In particular, we focus on SMDPs under the average-reward criterion. We present a new model-free RL algorithm called SMART (Semi-Markov Average Reward Technique). We present a detailed study of this algorithm on a combinatorially large problem of determining the optimal preventive maintenance schedule of a production inventory system. Numerical results from both the theoretical model and the RL algorithm are presented and compared.