Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning
Artificial Intelligence
Multiple model-based reinforcement learning
Neural Computation
Predictive state representations: a new theory for modeling dynamical systems
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Improving reinforcement learning with context detection
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Evaluating the performance of DCOP algorithms in a real world, dynamic problem
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 2
Opportunities for multiagent systems and multiagent reinforcement learning in traffic control
Autonomous Agents and Multi-Agent Systems
A Cascade Multiple Classifier System for Document Categorization
MCS '09 Proceedings of the 8th International Workshop on Multiple Classifier Systems
Learning in groups of traffic signals
Engineering Applications of Artificial Intelligence
To adapt or not to adapt: consequences of adapting driver and traffic light agents
ALAMAS'05/ALAMAS'06/ALAMAS'07 Proceedings of the 5th , 6th and 7th European conference on Adaptive and learning agents and multi-agent systems: adaptation and multi-agent learning
Mosaic for multiple-reward environments
Neural Computation
Autonomic multi-policy optimization in pervasive systems: Overview and evaluation
ACM Transactions on Autonomous and Adaptive Systems (TAAS) - Special section on formal methods in pervasive computing, pervasive adaptation, and self-adaptive systems: Models and algorithms
A market-inspired approach for intersection management in urban road traffic networks
Journal of Artificial Intelligence Research
Distributed and adaptive traffic signal control within a realistic traffic simulation
Engineering Applications of Artificial Intelligence
| Hi-index | 0.00 |
In this paper we introduce RL-CD, a method for solving reinforcement learning problems in non-stationary environments. The method is based on a mechanism for creating, updating and selecting one among several partial models of the environment. The partial models are incrementally built according to the system's capability of making predictions regarding a given sequence of observations. We propose, formalize and show the efficiency of this method both in a simple non-stationary environment and in a noisy scenario. We show that RL-CD performs better than two standard reinforcement learning algorithms and that it has advantages over methods specifically designed to cope with non-stationarity. Finally, we present known limitations of the method and future works.