Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

Plausibility-Based Heuristics for Latent Space Classical Planning (2306.11434v1)

Published 20 Jun 2023 in cs.AI

Abstract: Recent work on LatPlan has shown that it is possible to learn models for domain-independent classical planners from unlabeled image data. Although PDDL models acquired by LatPlan can be solved using standard PDDL planners, the resulting latent-space plan may be invalid with respect to the underlying, ground-truth domain (e.g., the latent-space plan may include hallucinatory/invalid states). We propose Plausibility-Based Heuristics, which are domain-independent plausibility metrics which can be computed for each state evaluated during search and uses as a heuristic function for best-first search. We show that PBH significantly increases the number of valid found plans on image-based tile puzzle and Towers of Hanoi domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. Exploration among and within Plateaus in Greedy Best-First Search. In Barbulescu, L.; Frank, J.; Mausam; and Smith, S. F., eds., Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling, ICAPS 2017, Pittsburgh, Pennsylvania, USA, June 18-23, 2017, 11–19. AAAI Press.
  2. Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary. In AAAI Conference on Artificial Intelligence, 6094–6101. AAAI Press.
  3. Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder. In Benton, J.; Lipovetzky, N.; Onaindia, E.; Smith, D. E.; and Srivastava, S., eds., Proceedings of the Twenty-Ninth International Conference on Automated Planning and Scheduling, ICAPS 2018, Berkeley, CA, USA, July 11-15, 2019, 592–600. AAAI Press.
  4. Classical Planning in Deep Latent Space. J. Artif. Intell. Res., 74: 1599–1686.
  5. STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving. Artificial Intelligence, 2(3): 189–208.
  6. A Formal Basis for the Heuristic Determination of Minimum Cost Paths. IEEE Transactions on Systems Science and Cybernetics, 4(2): 100–107.
  7. Landmarks, Critical Paths and Abstractions: What’s the Difference Anyway? In International Conference on Automated Planning and Scheduling(ICAPS), 162–169. AAAI.
  8. Merge-and-Shrink Abstraction: A Method for Generating Lower Bounds in Factored State Spaces. Journal of the ACM, 61(3): 16:1–16:63.
  9. Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786): 504–507.
  10. The FF Planning System: Fast Plan Generation Through Heuristic Search. Journal of Artificial Intelligence Research, 14: 253–302.
  11. VAL: Automatic Plan Validation, Continuous Effects and Mixed Initiative Planning Using PDDL. In 16th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2004), 15-17 November 2004, Boca Raton, FL, USA, 294–301. IEEE Computer Society.
  12. Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations(ICLR). OpenReview.net.
  13. Classical Planning with Simulators: Results on the Atari Video Games. In Yang, Q.; and Wooldridge, M. J., eds., Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI 2015, Buenos Aires, Argentina, July 25-31, 2015, 1610–1616. AAAI Press.
  14. The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. In International Conference on Learning Representations(ICLR). OpenReview.net.
  15. Steels, L. 2008. The Symbol Grounding Problem has been Solved. So What’s Next? In de Vega, M.; Glenberg, A.; and Graesser, A., eds., Symbols and Embodiment. Oxford University Press.

Summary

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