How to Reduce Action Space for Planning Domains? (Student Abstract)


  • Harsha Kokel The University of Texas at Dallas
  • Junkyu Lee IBM Research
  • Michael Katz IBM Research
  • Shirin Sohrabi IBM Research
  • Kavitha Srinivas IBM Research



Deterministic Planning, Planning With Markov Models, Reinforcement Learning


While AI planning and Reinforcement Learning (RL) solve sequential decision-making problems, they are based on different formalisms, which leads to a significant difference in their action spaces. When solving planning problems using RL algorithms, we have observed that a naive translation of the planning action space incurs severe degradation in sample complexity. In practice, those action spaces are often engineered manually in a domain-specific manner. In this abstract, we present a method that reduces the parameters of operators in AI planning domains by introducing a parameter seed set problem and casting it as a classical planning task. Our experiment shows that our proposed method significantly reduces the number of actions in the RL environments originating from AI planning domains.




How to Cite

Kokel, H., Lee, J., Katz, M., Sohrabi, S., & Srinivas, K. (2022). How to Reduce Action Space for Planning Domains? (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12989-12990.