Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Action Model Learning with Guarantees (2404.09631v1)

Published 15 Apr 2024 in cs.AI

Abstract: This paper studies the problem of action model learning with full observability. Following the learning by search paradigm by Mitchell, we develop a theory for action model learning based on version spaces that interprets the task as search for hypothesis that are consistent with the learning examples. Our theoretical findings are instantiated in an online algorithm that maintains a compact representation of all solutions of the problem. Among these range of solutions, we bring attention to actions models approximating the actual transition system from below (sound models) and from above (complete models). We show how to manipulate the output of our learning algorithm to build deterministic and non-deterministic formulations of the sound and complete models and prove that, given enough examples, both formulations converge into the very same true model. Our experiments reveal their usefulness over a range of planning domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. Learning action models with minimal observability. Artificial Intelligence, 275: 104–137.
  2. A comprehensive framework for learning declarative action models. Journal of Artificial Intelligence Research, 74: 1091–1123.
  3. Learning partially observable deterministic action models. Journal of Artificial Intelligence Research, 33: 349–402.
  4. A review of learning planning action models. The Knowledge Engineering Review, 33: e20.
  5. Learning First-Order Symbolic Representations for Planning from the Structure of the State Space. In ECAI 2020 - 24th European Conference on Artificial Intelligence, volume 325, 2322–2329.
  6. Acquiring planning domain models using LOCM. The Knowledge Engineering Review, 28(2): 195–213.
  7. PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains. J. Artif. Intell. Res., 20: 61–124.
  8. Automated Planning: theory and practice. Elsevier.
  9. A review of machine learning for automated planning. The Knowledge Engineering Review, 27(4): 433–467.
  10. Safe Learning of Lifted Action Models. In Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning, 379–389.
  11. Learning Probably Approximately Complete and Safe Action Models for Stochastic Worlds. In Thirty-Sixth AAAI Conference on Artificial Intelligence, 9795–9804.
  12. Kambhampati, S. 2007. Model-lite planning for the web age masses: The challenges of planning with incomplete and evolving domain models. In Proceedings of the National Conference on Artificial Intelligence, volume 22, 1601. Menlo Park, CA; Cambridge, MA; London; AAAI Press; MIT Press; 1999.
  13. LOUGA: learning planning operators using genetic algorithms. In Knowledge Management and Acquisition for Intelligent Systems: 15th Pacific Rim Knowledge Acquisition Workshop, 124–138. Springer.
  14. Online Learning of Action Models for PDDL Planning. In Zhou, Z., ed., Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, 4112–4118. ijcai.org.
  15. Programming by demonstration using version space algebra. Machine Learning, 53: 111–156.
  16. Version Space Algebra and its Application to Programming by Demonstration. In ICML, 527–534.
  17. McDermott, D.; et al. 1998. The planning domain definition language manual. Technical report, Technical Report 1165, Yale Computer Science, 1998.(CVC Report 98-003).
  18. McDermott, D. M. 2000. The 1998 AI planning systems competition. AI magazine, 21(2): 35–35.
  19. Mitchell, T. M. 1982. Generalization as search. Artificial intelligence, 18(2): 203–226.
  20. Learning Safe Numeric Action Models. In Thirty-Seventh AAAI Conference on Artificial Intelligence, 12079–12086.
  21. Learning STRIPS operators from noisy and incomplete observations. arXiv preprint arXiv:1210.4889.
  22. Classifier Learning from Noisy Data as Probabilistic Evidence Combination. In Proceedings of the 10th National Conference on Artificial Intelligence, 141–146.
  23. The LAMA planner: Guiding cost-based anytime planning with landmarks. Journal of Artificial Intelligence Research, 39: 127–177.
  24. PDDL Generators. https://doi.org/10.5281/zenodo.6382173.
  25. Efficient, Safe, and Probably Approximately Complete Learning of Action Models. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 4405–4411.
  26. Valiant, L. G. 1984. A theory of the learnable. Communications of the ACM, 27(11): 1134–1142.
  27. Asking the right questions: Learning interpretable action models through query answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 12024–12033.
  28. Learning action models from plan examples using weighted MAX-SAT. Artificial Intelligence, 171(2-3): 107–143.
  29. Action-model acquisition from noisy plan traces. In Twenty-Third International Joint Conference on Artificial Intelligence.
  30. Learning complex action models with quantifiers and logical implications. Artificial Intelligence, 174(18): 1540–1569.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now