Combinatorial optimization: algorithms and complexity
Combinatorial optimization: algorithms and complexity
The complexity of Markov decision processes
Mathematics of Operations Research
Empirical methods for artificial intelligence
Empirical methods for artificial intelligence
Planning under time constraints in stochastic domains
Artificial Intelligence - Special volume on planning and scheduling
Phase transitions and the search problem
Artificial Intelligence - Special volume on frontiers in problem solving: phase transitions and complexity
Predicting real-time planner performance by domain characterization
Predicting real-time planner performance by domain characterization
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
Local Search Algorithms for SAT: An Empirical Evaluation
Journal of Automated Reasoning
Near-Optimal Reinforcement Learning in Polynominal Time
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Algorithm Selection using Reinforcement Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Model based Bayesian exploration
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Autonomous behaviors for interactive vehicle animations
SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
Autonomous behaviors for interactive vehicle animations
Graphical Models - Special issue on SCA 2004
Agent influence as a predictor of difficulty for decentralized problem-solving
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Journal of Intelligent and Robotic Systems
Hi-index | 0.01 |
Problem characteristics often have a significant influence on the difficulty of solving optimization problems. In this paper, we propose attributes for characterizing Markov Decision Processes (MDPs), and discuss how they affect the performance of reinforcement learning algorithms that use function approximation. The attributes measure mainly the amount of randomness in the environment. Their values can be calculated from the MDP model or estimated on-line. We show empirically that two of the proposed attributes have a statistically significant effect on the quality of learning. We discuss how measurements of the proposed MDP attributes can be used to facilitate the design of reinforcement learning systems.