Seeing the Forest Despite the Trees: Large Scale Spatial-Temporal Decision Making
This addresses real-world spatial-temporal planning challenges for domains like forestry, though it is incremental as it adapts existing RL methods to a specific problem type.
The paper tackles the Large Scale Spatial-Temporal (LSST) planning problem, such as forestry planning, by formulating it as a reinforcement learning problem and using policy gradients, showing that an abstract policy outperforms an explicit one with higher rewards and fewer parameters.
We introduce a challenging real-world planning problem where actions must be taken at each location in a spatial area at each point in time. We use forestry planning as the motivating application. In Large Scale Spatial-Temporal (LSST) planning problems, the state and action spaces are defined as the cross-products of many local state and action spaces spread over a large spatial area such as a city or forest. These problems possess state uncertainty, have complex utility functions involving spatial constraints and we generally must rely on simulations rather than an explicit transition model. We define LSST problems as reinforcement learning problems and present a solution using policy gradients. We compare two different policy formulations: an explicit policy that identifies each location in space and the action to take there; and an abstract policy that defines the proportion of actions to take across all locations in space. We show that the abstract policy is more robust and achieves higher rewards with far fewer parameters than the elementary policy. This abstract policy is also a better fit to the properties that practitioners in LSST problem domains require for such methods to be widely useful.