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.
- 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.
- Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary. In AAAI Conference on Artificial Intelligence, 6094–6101. AAAI Press.
- 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.
- Classical Planning in Deep Latent Space. J. Artif. Intell. Res., 74: 1599–1686.
- STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving. Artificial Intelligence, 2(3): 189–208.
- A Formal Basis for the Heuristic Determination of Minimum Cost Paths. IEEE Transactions on Systems Science and Cybernetics, 4(2): 100–107.
- Landmarks, Critical Paths and Abstractions: What’s the Difference Anyway? In International Conference on Automated Planning and Scheduling(ICAPS), 162–169. AAAI.
- Merge-and-Shrink Abstraction: A Method for Generating Lower Bounds in Factored State Spaces. Journal of the ACM, 61(3): 16:1–16:63.
- Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786): 504–507.
- The FF Planning System: Fast Plan Generation Through Heuristic Search. Journal of Artificial Intelligence Research, 14: 253–302.
- 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.
- Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations(ICLR). OpenReview.net.
- 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.
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. In International Conference on Learning Representations(ICLR). OpenReview.net.
- 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.