REDUCING THE SEARCH SPACE IN SYMBOLIC PLANNING USING NEURAL COST ESTIMATION
Keywords:
GOAP, symbolic planning, neural cost estimation, search space, agent behavior, hybrid methodsAbstract
The objective of this work is to reduce the search space in GOAP by integrating a neural cost estimation model. A symbolic GOAP-based planner is implemented and extended with a neural evaluation component that adds an additional cost term based on state and action features. A simulation environment is developed to evaluate the proposed approach.
References
Russell S., Norvig P. Artificial Intelligence: A Modern Approach. 4th ed. Harlow: Pearson, 2021. 1136 p. (pp. 92–99).
Ghallab M., Nau D., Traverso P. Automated Planning: Theory and Practice. San Francisco: Morgan Kaufmann, 2004. 633 p. (pp. 24–30, 70–72).
Sutton R. S., Barto A. G. Reinforcement Learning: An Introduction. 2nd ed. Cambridge: MIT Press, 2018. 552 p. (pp. 98–105).
Orkin J. Three States and a Plan: The AI of F.E.A.R. // Proceedings of the Game Developers Conference. 2006. URL: https://web.archive.org/web/20230912172958/https://alumni.media.mit.edu/~jorkin/gdc2006_orkin_jeff_fear.pdf (access date: 23.04.2026).
Silver D. et al. Mastering the game of Go with deep neural networks and tree search // Nature. 2016. Vol. 529. P. 484–489.
Mnih V. et al. Human-level control through deep reinforcement learning // Nature. 2015. Vol. 518. P. 529–533.
