Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learning
This work addresses the challenge of inefficient planning in AI by enabling parallel execution, which is incremental as it builds on existing RL methods with a novel action space modification.
The paper tackles the problem of applying reinforcement learning to AI planning by introducing meta-operators, which allow multiple planning operators to be applied simultaneously, enabling parallel planning and improving performance in domains where previous generalized planning models failed, with results showing enhanced outcomes in specific benchmarks.
There is a growing interest in the application of Reinforcement Learning (RL) techniques to AI planning with the aim to come up with general policies. Typically, the mapping of the transition model of AI planning to the state transition system of a Markov Decision Process is established by assuming a one-to-one correspondence of the respective action spaces. In this paper, we introduce the concept of meta-operator as the result of simultaneously applying multiple planning operators, and we show that including meta-operators in the RL action space enables new planning perspectives to be addressed using RL, such as parallel planning. Our research aims to analyze the performance and complexity of including meta-operators in the RL process, concretely in domains where satisfactory outcomes have not been previously achieved using usual generalized planning models. The main objective of this article is thus to pave the way towards a redefinition of the RL action space in a manner that is more closely aligned with the planning perspective.