Compositional Planning Using Optimal Option Models
This work addresses hierarchical planning in reinforcement learning, offering a novel compositional approach that could improve efficiency in complex decision-making tasks.
The paper tackles the problem of hierarchical reinforcement learning by introducing a framework for compositional planning through optimal option models, achieving a unified view of intra- and inter-option model learning via a generalized Bellman equation.
In this paper we introduce a framework for option model composition. Option models are temporal abstractions that, like macro-operators in classical planning, jump directly from a start state to an end state. Prior work has focused on constructing option models from primitive actions, by intra-option model learning; or on using option models to construct a value function, by inter-option planning. We present a unified view of intra- and inter-option model learning, based on a major generalisation of the Bellman equation. Our fundamental operation is the recursive composition of option models into other option models. This key idea enables compositional planning over many levels of abstraction. We illustrate our framework using a dynamic programming algorithm that simultaneously constructs optimal option models for multiple subgoals, and also searches over those option models to provide rapid progress towards other subgoals.