Abstract
We propose and evaluate an adaptive reinforcement learning system that integrates both exploitation- and exploration-oriented learning (ArLee). Compared to conventional reinforcement learning, ArLee is more robust in a dynamically changing environment and conducts exploration-oriented learning efficiently even in a large-scale environment. It is thus well suited for autonomous systems, for example, software agents and mobile robots, that operate in dynamic, large-scale environments, such as the real world and the Internet. Simulation demonstrates the learning system's basic effectiveness.
| Original language | English |
|---|---|
| Pages (from-to) | 474-478 |
| Number of pages | 5 |
| Journal | Journal of Advanced Computational Intelligence and Intelligent Informatics |
| Volume | 3 |
| Issue number | 6 |
| DOIs | |
| Publication status | Published - 1999 Dec |
| Externally published | Yes |
Keywords
- Dynamic environment
- Exploitation-oriented learning
- Exploration-oriented learning
- Multi-agent model
- Reinforcement learning
ASJC Scopus subject areas
- Human-Computer Interaction
- Computer Vision and Pattern Recognition
- Artificial Intelligence
Fingerprint
Dive into the research topics of 'Adaptive Reinforcement Learning Integrating Exploitation-and Exploration-oriented Learning'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS