TY - GEN
T1 - Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand
AU - Garces, Daniel
AU - Bhattacharya, Sushmita
AU - Gil, Stephanie
AU - Bertsekas, Dimitri
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - We derive a learning framework to generate routing/pickup policies for a fleet of autonomous vehicles tasked with servicing stochastically appearing requests on a city map. We focus on policies that 1) give rise to coordination amongst the vehicles, thereby reducing wait times for servicing requests, 2) are non-myopic, and consider a-priori potential future requests, 3) can adapt to changes in the underlying demand distribution. Specifically, we are interested in policies that are adaptive to fluctuations of actual demand conditions in urban environments, such as on-peak vs. off-peak hours. We achieve this through a combination of (i) an online play algorithm that improves the performance of an offline-trained policy, and (ii) an offline approximation scheme that allows for adapting to changes in the underlying demand model. In particular, we achieve adaptivity of our learned policy to different demand distributions by quantifying a region of validity using the q-valid radius of a Wasserstein Ambiguity Set. We propose a mechanism for switching the originally trained offline approximation when the current demand is outside the original validity region. In this case, we propose to use an offline architecture, trained on a historical demand model that is closer to the current demand in terms of Wasserstein distance. We learn routing and pickup policies over real taxicab requests in San Francisco with high variability between on-peak and off-peak hours, demonstrating the ability of our method to adapt to real fluctuation in demand distributions. Our numerical results demonstrate that our method outperforms alternative rollout-based reinforcement learning schemes, as well as other classical methods from operations research.
AB - We derive a learning framework to generate routing/pickup policies for a fleet of autonomous vehicles tasked with servicing stochastically appearing requests on a city map. We focus on policies that 1) give rise to coordination amongst the vehicles, thereby reducing wait times for servicing requests, 2) are non-myopic, and consider a-priori potential future requests, 3) can adapt to changes in the underlying demand distribution. Specifically, we are interested in policies that are adaptive to fluctuations of actual demand conditions in urban environments, such as on-peak vs. off-peak hours. We achieve this through a combination of (i) an online play algorithm that improves the performance of an offline-trained policy, and (ii) an offline approximation scheme that allows for adapting to changes in the underlying demand model. In particular, we achieve adaptivity of our learned policy to different demand distributions by quantifying a region of validity using the q-valid radius of a Wasserstein Ambiguity Set. We propose a mechanism for switching the originally trained offline approximation when the current demand is outside the original validity region. In this case, we propose to use an offline architecture, trained on a historical demand model that is closer to the current demand in terms of Wasserstein distance. We learn routing and pickup policies over real taxicab requests in San Francisco with high variability between on-peak and off-peak hours, demonstrating the ability of our method to adapt to real fluctuation in demand distributions. Our numerical results demonstrate that our method outperforms alternative rollout-based reinforcement learning schemes, as well as other classical methods from operations research.
UR - http://www.scopus.com/inward/record.url?scp=85165631901&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85165631901&partnerID=8YFLogxK
U2 - 10.1109/ICRA48891.2023.10161067
DO - 10.1109/ICRA48891.2023.10161067
M3 - Conference contribution
AN - SCOPUS:85165631901
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 3524
EP - 3531
BT - Proceedings - ICRA 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Robotics and Automation, ICRA 2023
Y2 - 29 May 2023 through 2 June 2023
ER -