Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling

TL;DR

This paper introduces CEVD, a novel method for scalable ride pooling that considers inter-agent dependencies via conditional expectations, significantly improving request fulfillment in city-wide datasets.

Contribution

The paper proposes CEVD, a new value decomposition approach that captures dependencies among agents without increasing computational complexity, enhancing ride pooling performance.

Findings

CEVD outperforms NeurADP by up to 9.76% in requests served.

The approach effectively models agent dependencies using joint conditional probabilities.

Significant improvements demonstrated on a city-wide taxi dataset.

Abstract

Owing to the benefits for customers (lower prices), drivers (higher revenues), aggregation companies (higher revenues) and the environment (fewer vehicles), on-demand ride pooling (e.g., Uber pool, Grab Share) has become quite popular. The significant computational complexity of matching vehicles to combinations of requests has meant that traditional ride pooling approaches are myopic in that they do not consider the impact of current matches on future value for vehicles/drivers. Recently, Neural Approximate Dynamic Programming (NeurADP) has employed value decomposition with Approximate Dynamic Programming (ADP) to outperform leading approaches by considering the impact of an individual agent's (vehicle) chosen actions on the future value of that agent. However, in order to ensure scalability and facilitate city-scale ride pooling, NeurADP completely ignores the impact of other agents actions on individual agent/vehicle value. As demonstrated in our experimental results, ignoring the impact of other agents actions on individual value can have a significant impact on the overall performance when there is increased competition among vehicles for demand. Our key contribution is a novel mechanism based on computing conditional expectations through joint conditional probabilities for capturing dependencies on other agents actions without increasing the complexity of training or decision making. We show that our new approach, Conditional Expectation based Value Decomposition (CEVD) outperforms NeurADP by up to 9.76% in terms of overall requests served, which is a significant improvement on a city wide benchmark taxi dataset.