Knowledge transfer for deep reinforcement learning with hierarchical experience replay

31st AAAI Conference on Artificial Intelligence, AAAI 2017

Volumn , Issue , 2017, Pages 1640-1646

  Yin, Haiyan ^a   Pan, Sinno Jialin ^a  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; DEEP LEARNING; DISTILLATION; KNOWLEDGE MANAGEMENT;

COMPUTATIONAL EFFORT; KNOWLEDGE TRANSFER; POLICY NETWORKS; TASK DOMAIN; TESTING ENVIRONMENT;

REINFORCEMENT LEARNING;

EID: 85030470931     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (25)

1. Ba, J., and Caruana, R. 2014. Do deep nets really need to be deep? In NIPS, 2654-2662.
2. Bucilu, C.; Caruana, R.; and Niculescu-Mizil, A. 2006. Model compression. In SIGKDD, 535-541. ACM.
3. Finn, C.; Levine, S.; and Abbeel, P. 2016. Guided cost learning: Deep inverse optimal control via policy optimization. arXiv preprint arXiv:1603.00448.
4. Guo, H. 2015. Generating text with deep reinforcement learning. arXiv preprint arXiv:1510.09202.
5. Hinton, G.; Vinyals, O.; and Dean, J. 2014. Distilling the knowledge in a neural network. In NIPS Workshop on Deep Learning and Representation Learning.
6. Levine, S.; Finn, C.; Darrell, T.; and Abbeel, P. 2016. End-to-end training of deep visuomotor policies. JMLR 17(39):1-40.
7. Li, J.; Zhao, R.; Huang, J.-T.; and Gong, Y. 2014. Learning small-size dnn with output-distribution-based criteria. In Interspeech, 1910-1914.
8. Li, J.; Monroe, W.; Ritter, A.; and Jurafsky, D. 2016. Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541.
9. Lin, L.-J. 1992. Reinforcement Learning for Robots Using Neural Networks. Ph.D. Dissertation, Pittsburgh, PA, USA. UMI Order No. GAX93-22750.
10. Mnih, V.; Kavukcuoglu, K.; Silver, D.; a Rusu, A.; Veness, J.; Bellemare, M. G.; Graves, A.; Riedmiller, M.; Fidjeland, A. K.; Ostrovski, G.; Petersen, S.; C. Beattie, A. S.; Antonoglou, I.; H. King, D. K.; Wierstra, D.; Legg, S.; and Hassabis, D. 2015. Human-level control through deep reinforcement learning. Nature.
11. Moore, A. W., and Atkeson, C. G. 1993. Prioritized sweeping: Reinforcement learning with less data and less time. Machine Learning 13(1):103-130.
12. Pan, S. J., and Yang, Q. 2010. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22(10):1345-1359.
13. Parisotto, E.; Ba, J.; and Salakhutdinov, R. 2016. Actormimic deep multitask and transfer reinforcement learning. In ICLR.
14. Parr, D. A. N. F. R. 1998. Generalized prioritized sweeping. In NIPS.
15. Romero, A.; Ballas, N.; Kahou, S. E.; Chassang, A.; Gatta, C.; and Bengio, Y. 2015. Fitnets: Hints for thin deep nets. In ICLR.
16. Rosenstein, M. T.; Marx, Z.; Kaelbling, L. P.; and Dietterich, T. G. 2005. To transfer or not to transfer. In NIPS Workshop on Inductive Transfer: 10 Years Later.
17. Rusu, A. A.; Colmenarejo, S. G.; Gulcehre, C.; Desjardins, G.; Kirkpatrick, J.; Pascanu, R.; Mnih, V.; Kavukcuoglu, K.; and Hadsell, R. 2016. Policy distillation. In ICLR.
18. Schaul, T.; Quan, J.; Antonoglou, I.; and Silver, D. 2016. Prioritized experience replay. In ICLR.
19. Seijen, H. V., and Sutton, R. S. 2013. Planning by prioritized sweeping with small backups. In ICML, 361-369.
20. Sutton, R. S., and Barto, A. G. 1998. Introduction to Reinforcement Learning. Cambridge, MA, USA: MIT Press, 1st edition.
21. Tang, Z.; Wang, D.; Pan, Y.; and Zhang, Z. 2015. Knowledge transfer pre-training. arXiv preprint arXiv:1506.02256.
22. Tieleman, T., and Hinton, G. 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning.
23. Van Hasselt, H.; Guez, A.; and Silver, D. 2016. Deep reinforcement learning with double q-learning. In AAAI, 2094-2100.
24. Zahavy, T.; Zrihem, N. B.; and Mannor, S. 2016. Graying the black box: Understanding dqns. In ICML, 1899-1908.
25. Zhang, M.; McCarthy, Z.; Finn, C.; Levine, S.; and Abbeel, P. 2016. Learning deep neural network policies with continuous memory states. In ICRA, 520-527. IEEE.