Model-based Policy Gradient Reinforcement Learning

Proceedings, Twentieth International Conference on Machine Learning

Volumn 2, Issue , 2003, Pages 776-783

  Wang, Xin ^a   Dietterich, Thomas G ^a  

^a Oregon State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

POLICY GRADIENT METHODS; REINFORCEMENT LEARNING; RESOURCE-CONSTRAINED SCHEDULING; STOCHASTIC POLICIES;

ALGORITHMS; BENCHMARKING; HEURISTIC METHODS; MATHEMATICAL MODELS; MATRIX ALGEBRA; MONTE CARLO METHODS; RANDOM PROCESSES; SCHEDULING;

LEARNING SYSTEMS;

EID: 1942451973     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. Aberdeen, D., & Baxter, J. (2002). Scalable internal-state policy-gradient methods for POMDPs. ICML-2002 (pp. 3-10). Morgan Kaufmann.
2. Baxter, J., & Barlett, P. (2000). Reinforcement learning in POMDPs via direct gradient ascent. ICML-2000 (pp. 41-48). Cambridge, MA: The MIT Press.
3. Boutilier, C., Dearden, R., & Goldszmidt, M. (1995). Exploiting structure in policy construction. IJCAI-1995 (pp. 1104-1111). San Francisco: Morgan Kaufmann.
4. Dietterich, T. G., & Wang, X. (2002). Batch value function approximation via support vectors. NIPS-2001 (pp. 1491-1498). Cambridge, MA: The MIT Press.
5. Greensmith, E., Bartlett, P., & Baxter, J. (2002). Variance reduction techniques for gradient estimates in reinforcement learning. NIPS-2001 (pp. 1507-1514). Cambridge, MA: The MIT Press.
6. Guestrin, C., Koller, D., & Parr, R. (2001). Max-norm projections for factored MDPs. IJCAI-2001 (pp. 673-682).
7. Harvey, W. D., & Ginsberg, M. L. (1995). Limited discrepancy search. IJCAI-95 (pp. 607-615). Montréal, Québec, Canada: Morgan Kaufmann, 1995.
8. Kearns, M., Mansour, Y., & Ng, A. Y. (2000). Approximate learning in large POMDPs via reusable trajectories. NIPS-1999 (pp. 1001-1007). Cambridge, MA: The MIT Press.
9. Kim, K.-E., Dean, T., & Meuleau, N. (2000). Approximates solutions to factored markov decision processes via greedy search in the space of finite state controllers. Artificial Intelligence Planning Systems (pp. 323-330).
10. Konda, V. R., & Tsitsiklis, J. N. (2000). Actor-critic algorithms. NIPS-1999. Cambridge, MA: The MIT Press.
11. Munos, R., & Moore, A. (2002). Variable resolution discretization in optimal control. Machine Learning, 49, 291-323.
12. Ng, A. Y., Parr, R., & Koller, D. (2000). Policy search via density estimation. NIPS-1999. Cambridge, MA: The MIT Press.
13. Peshkin, L., Meuleau, N., & Kaelbling, L. P. (1999). Learning policies with external memory. ICML-1999 (pp. 307-314). Cambridge, MA: The MIT Press.
14. Russell, S., & Norvig, P. (1995). Artificial intelligence, a modern approach. Prentice Hall.
15. Shelton, C. R. (2001). Policy improvement for POMDPs using normalized importance sampling. UAI-2001 (pp. 496-503).
16. Sutton, R., & Barto, A. (1998). Reinforcement learning: an introduction. Cambridge, MA: MIT Press.
17. Sutton, R. S., McAllester, D., Singh, S., & Mansour, Y. (2000). Policy gradient methods for reinforcement learning with function approximation. NIPS-1999 (pp. 1057-1063). Cambridge, MA: The MIT Press.
18. Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8, 229-256.
19. Zhang, W., & Dietterich, T. G. (1995). A reinforcement learning approach to job-shop scheduling. IJCAI-1995 (pp. 1114-1120).