Autonomous shaping: Knowledge transfer in reinforcement learning
Publication
, Journal Article
Konidaris, G; Barto, A
Published in: ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning
October 6, 2006
We introduce the use of learned shaping rewards in reinforcement learning tasks, where an agent uses prior experience on a sequence of tasks to learn a portable predictor that estimates intermediate rewards, resulting in accelerated learning in later tasks that are related but distinct. Such agents can be trained on a sequence of relatively easy tasks in order to develop a more informative measure of reward that can be transferred to improve performance on more difficult tasks with-out requiring a hand coded shaping function. We use a rod positioning task to show that this significantly improves performance even after a very brief training period.
Duke Scholars
Published In
ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning
Publication Date
October 6, 2006
Volume
2006
Start / End Page
489 / 496
Citation
APA
Chicago
ICMJE
MLA
NLM
Konidaris, G., & Barto, A. (2006). Autonomous shaping: Knowledge transfer in reinforcement learning. ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning, 2006, 489–496.
Konidaris, G., and A. Barto. “Autonomous shaping: Knowledge transfer in reinforcement learning.” ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning 2006 (October 6, 2006): 489–96.
Konidaris G, Barto A. Autonomous shaping: Knowledge transfer in reinforcement learning. ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning. 2006 Oct 6;2006:489–96.
Konidaris, G., and A. Barto. “Autonomous shaping: Knowledge transfer in reinforcement learning.” ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning, vol. 2006, Oct. 2006, pp. 489–96.
Konidaris G, Barto A. Autonomous shaping: Knowledge transfer in reinforcement learning. ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning. 2006 Oct 6;2006:489–496.
Published In
ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning
Publication Date
October 6, 2006
Volume
2006
Start / End Page
489 / 496