Technical Note: \cal Q-Learning
Machine Learning
Machine Learning
Shape quantization and recognition with randomized trees
Neural Computation
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Random Subspace Method for Constructing Decision Forests
IEEE Transactions on Pattern Analysis and Machine Intelligence
Reinforcement Learning
Machine Learning
Reinforcement Learning in the Multi-Robot Domain
Autonomous Robots
An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Reinforcement Learning with Bounded Risk
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
An Overview of MAXQ Hierarchical Reinforcement Learning
SARA '02 Proceedings of the 4th International Symposium on Abstraction, Reformulation, and Approximation
Combining Pattern Classifiers: Methods and Algorithms
Combining Pattern Classifiers: Methods and Algorithms
Exploration and apprenticeship learning in reinforcement learning
ICML '05 Proceedings of the 22nd international conference on Machine learning
IDEAS '07 Proceedings of the 11th International Database Engineering and Applications Symposium
Geometrically exact dynamic splines
Computer-Aided Design
Multi-robot Cooperation Based on Hierarchical Reinforcement Learning
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part III: ICCS 2007
Risk-sensitive reinforcement learning applied to control under constraints
Journal of Artificial Intelligence Research
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
A novel low-cost, limited-resource approach to autonomous multi-robot exploration and mapping
Robotics and Autonomous Systems
Information Sciences: an International Journal
An incremental extremely random forest classifier for online learning and tracking
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Linked multi-component mobile robots: Modeling, simulation and control
Robotics and Autonomous Systems
Open-ended evolution as a means to self-organize heterogeneous multi-robot systems in real time
Robotics and Autonomous Systems
Modeling and Optimization of Adaptive Foraging in Swarm Robotic Systems
International Journal of Robotics Research
Distributed consensus algorithms for merging feature-based maps with limited communication
Robotics and Autonomous Systems
Self-organizing state aggregation for architecture design of Q-learning
Information Sciences: an International Journal
A review on modelling, implementation, and control of snake robots
Robotics and Autonomous Systems
Reinforcement learning for MDPs with constraints
ECML'06 Proceedings of the 17th European conference on Machine Learning
Development of membrane controllers for mobile robots
Information Sciences: an International Journal
A Comprehensive Survey of Multiagent Reinforcement Learning
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
SVM-Based Tree-Type Neural Networks as a Critic in Adaptive Critic Designs for Control
IEEE Transactions on Neural Networks
Multi-robot coalition formation in real-time scenarios
Robotics and Autonomous Systems
Robotics and Autonomous Systems
Multilevel-based topology design and shape control of robot swarms
Automatica (Journal of IFAC)
IMPROVING THE CONTROL OF SINGLE ROBOT HOSE TRANSPORT
Cybernetics and Systems - LEARNING, SCHEDULING, RESOURCE OPTIMIZATION, AND EVOLUTION IN SMART ARTIFICIAL SYSTEMS: CHALLENGES AND SUPPORT
Hi-index | 0.07 |
The paper deals with the problem of learning the control of Multi-Component Robotic Systems (MCRSs) applying Multi-Agent Reinforcement Learning (MARL) algorithms. Modeling Linked MCRS usually leads to over-constrained environments, posing great difficulties for efficient learning with conventional single and multi-agent reinforcement algorithms. In this paper, we propose a hybrid learning algorithm composed of a modified Q-Learning algorithm embedding an Undesired State-Action Prediction (USAP) module trained by a supervised learning approach which learns a model predicting undesired transitions to states breaking physical constraints. The USAP module's output is used by the Q-Learning algorithm to prevent these undesired transitions, therefore boosting learning efficiency. This hybrid approach is extended to the multi-agent case embedding the USAP module in Distributed Round-Robin Q-Learning (D-RR-QL), which requires very little communications among agents. We present results of computational experiments conducted in the classical multi-agent taxi scheduling task and a hose transportation task. Results show a considerable learning gain both in time and accuracy, compared to the state-of-the-art Distributed Q-Learning approach in the deterministic taxi scheduling task. In the hose transportation task, USAP module introduces a significant improvement in learning convergence speed.