Transfer in reinforcement learning via Markov logic networks

AAAI Workshop - Technical Report

Volumn WS-08-13, Issue , 2008, Pages 49-54

  Torrey, Lisa ^a   Shavlik, Jude ^a   Natarajan, Sriraam ^a   Kuppili, Pavan ^a   Walker, Trevor ^a  

^a University of Wisconsin Madison   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EARLY LEARNING; MARKOV LOGIC NETWORKS; PERFORMANCE BENEFITS; Q-FUNCTION; ROBOCUP; SOCCER DOMAIN; SPEED-UP; STATISTICAL RELATIONAL LEARNING;

REINFORCEMENT; REINFORCEMENT LEARNING; TARGETS;

EDUCATION;

EID: 66149165875     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (23)

1. Croonenborghs, T.; Driessens, K.; and Bruynooghe, M. 2007. Learning relational skills for inductive transfer in relational reinforcement learning. In 2007 International Conference on Inductive Logic Programming.
2. Fernandez, F., and Veloso, M. 2006. Policy reuse for transfer learning across tasks with different state and action spaces. In 2006 ICML Workshop on Structural Knowledge Transfer for Machine Learning.
3. Goadrich, M.; Oliphant, L.; and Shavlik, J. 2006. Gleaner: creating ensembles of first-order clauses to improve recall-precision curves. Machine Learning 64:231-261.
4. Kok, S.; Singla, P.; Richardson, M.; and Domingos, P. 2005. The Alchemy system for statistical relational AI. Technical report, University of Washington.
5. Lowd, D., and Domingos, P. 2007. Efficient weight learning for markov logic networks. In 2007 Conference on Knowledge Discovery in Databases.
6. Maclin, R.; Shavlik, J.; Torrey, L.; and Walker, T. 2005. Knowledge-based support vector regression for reinforcement learning. In 2005 IJCAI Workshop on Reasoning, Representation, and Learning in Computer Games.
7. Mihalkova, L., and Mooney, R. 2006. Transfer learning with Markov logic networks. In 2006 ICML Workshop on Structural Knowledge Transfer for Machine Learning.
8. Mihalkova, L.; Huynh, T.; and Mooney, R. 2007. Mapping and revising Markov logic networks for transfer learning. In 2007 AAAI Conference on Artificial Intelligence.
9. Natarajan, S.; Tadepalli, P.; and Fern, A. 2007. A relational hierarchical model for decision-theoretic assistance. In 2007 International Conference on Inductive Logic Programming.
10. Noda, I.; Matsubara, H.; Hiraki, K.; and Frank, I. 1998. Soccer server: A tool for research on multiagent systems. Applied Artificial Intelligence 12:233-250.
11. Ramon, J.; Driessens, K.; and Croonenborghs, T. 2007. Transfer learning in reinforcement learning problems through partial policy recycling. In 2007 European Conference on Machine Learning.
12. Richardson, M., and Domingos, P. 2005. Markov logic networks. Machine Learning 62:107-136.
13. Srinivasan, A. 2001. The Aleph manual (available online).
14. Stone, P., and Sutton, R. 2001. Scaling reinforcement learning toward RoboCup soccer. In 2001 International Conference on Machine Learning.
15. Sutton, R., and Barto, A. 1998. Reinforcement Learning: An Introduction. MIT Press.
16. Sutton, R. 1988. Learning to predict by the methods of temporal differences. Machine Learning 3:9-44.
17. Tadepalli, P.; Givan, R.; and Driessens, K. 2004. Relational reinforcement learning: An overview. In 2004 ICML Workshop on Relational Reinforcement Learning.
18. Taylor, M., and Stone, P. 2007. Cross-domain transfer for reinforcement learning. In 2007 International Conference on Machine Learning.
19. Taylor, M.; Stone, P.; and Liu, Y. 2005. Value functions for RL-based behavior transfer: A comparative study. In 2005 AAAI Conference on Artificial Intelligence.
20. Torrey, L.; Walker, T.; Shavlik, J.; and Maclin, R. 2005. Using advice to transfer knowledge acquired in one reinforcement learning task to another. In 2005 European Conference on Machine Learning.
21. Torrey, L.; Shavlik, J.; Walker, T.; and Maclin, R. 2006. Skill acquisition via transfer learning and advice taking. In 2006 European Conference on Machine Learning.
22. Torrey, L.; Shavlik, J.; Walker, T.; and Maclin, R. 2007. Relational macros for transfer in reinforcement learning. In 2007 International Conference on Inductive Logic Programming.
23. Watkins, C. 1989. Learning from delayed rewards. Ph.D. Dissertation, University of Cambridge.