Object focused Q-learning for autonomous agents

12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013

Volumn 2, Issue , 2013, Pages 1061-1068

  Cobo, Luis C ^a   Isbell Jr , Charles L ^a   Thomaz, Andrea L ^a  

^a Georgia Institute of Technology   (United States)

Author keywords

Modular RL; Reinforcement learning; State abstraction; Task decomposition

Indexed keywords

AUTONOMOUS AGENTS; LEARNING ALGORITHMS; MULTI AGENT SYSTEMS; RISK PERCEPTION;

ARBITRATION ALGORITHM; CONTROL POLICY; INDEPENDENT OBJECTS; MODULAR RL; OBJECT CLASS; STATE ABSTRACTION; TASK DECOMPOSITION; TWO DOMAINS;

REINFORCEMENT LEARNING;

EID: 84899422939     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. COWAN, N. The magical mystery four: How is working memory capacity limited, and why? Current Directions in Psychological Science 19 (Feb. 2010), 51-57.
2. DIETTERICH, T. The MAXQ method for hierarchical reinforcement learning. In Proc. Int. Conf. on Machine Learning (1998), pp. 118-126.
3. DIUK, C, COHEN, A., and LITTMAN, M. An object-oriented representation for efficient reinforcement learning. In Proc. Int. Conf. on Machine Learning (2008), ACM, pp. 240-247.
4. DZEROSKI, S., and RAEDT., L. D., and BLOCKEEL, H. Relational reinforcement learning. In Proc. Int. Conf. on Machine Learning (1998), ACM, pp. 136-143.
5. FERN, A., YOON, S., and GIVAN, R. Approximate policy iteration with a policy language bias. In Advances in Neural Information Processing Systems (2003), pp. 8-13.
6. GREINER, R. PALO: A probabilistic hill-climbing algorithm. Artificial Intelligence 84, 1 (1996), 177-208.
7. GUESTRIN, C, KOLLER, D., GEARHART, C, and KANODIA, N. Generalizing plans to new environments in relational MDPs. In Proc. of the Int. Joint Conf. on Artificial Intelligence (2003).
8. HENGST, B. Discovering hierarchy in reinforcement learning with HEXQ. In Proc. Int. Conf. on Machine Learning (2002), pp. 234-250.
9. JONSSON, A., and BARTO, A. Automated state abstraction for options using the U-tree algorithm. Advances in Neural Information Processing Systems (2001), 1054-1060.
10. KEARNS, M., and SINGH, S. Finite-sample convergence rates for q-learning and indirect algorithms. Advances in Neural Information Processing Systems (1999), 996-1002.
11. KIRKPATRICK, S., and GELATT., C. D., and VECCHI, M. P. Optimization by simulated annealing. Science 220, 4598 (1983), 671-680.
12. KONIDARIS, G., and BARTO, A. Efficient skill learning using abstraction selection. In Int. Joint Conf. on Artificial Intelligence (2009), pp. 1107-1112.
13. RUSSELL, S., and ZIMDARS, A. Q-decomposition for reinforcement learning agents. In Proc. Int. Conf. on Machine Learning (2003).
14. SEIJEN, H. V., WHITESON, S., and KESTER, L. Switching between representations in reinforcement learning. In Interactive Collaborative Information Systems. 2010, pp. 65-84.
15. SIMSEK, O., and BARTO, A. G. Using relative novelty to identify useful temporal abstractions in reinforcement learning. Proc. Int. Conf. on Machine Learning (2004), 95.
16. SPRAGUE, N., and BALLARD, D. Multiple-goal reinforcement learning with modular sarsa(O). In Int. Joint Conf. on Artificial Intelligence (2003).
17. STOLLE, M., and PRECUP, D. Learning Options in Reinforcement Learning. Abstraction, Reformulation, and Approximation (2002), 212-223.
18. TALVITIE, E., and SINGH, S. Simple Local Models for Complex Dynamical Systems. In Advances in Neural Information Processing Systems (2008).
19. VAN OTTERLO, M. A survey of reinforcement learning in relational domains. In CTIT Technical Report Series, ISSN 1381-3625 (2005).
20. VIGORITO, C. M., and BARTO, A. G. Intrinsically Motivated Hierarchical Skill Learning in Structured Environments. IEEE Trans, on Autonomous Mental Development 2, 2 (2010), 132-143.
21. WATKINS, C. J. C. H., and DAYAN, P. Q-learning. Machine Learning 8 (1992), 279-292.
22. WILSON, T. Strangers to ourselves: Discovering the adaptive unconscious. Belknap Press, 2004.