A Distributed Reinforcement Learning Solution With Knowledge Transfer Capability for A Bike Rebalancing Problem
This addresses the critical service bottleneck of manual bike rebalancing for transportation operators, offering a smart autonomous solution, though it appears incremental as it builds on existing RL and transfer learning concepts.
The paper tackled the bike rebalancing problem in transportation services like Citi Bike by proposing a Distributed Reinforcement Learning (DiRL) solution with Transfer Learning capability, achieving a 350% improvement in autonomous bike rebalancing and a 62.4% performance boost in network management.
Rebalancing is a critical service bottleneck for many transportation services, such as Citi Bike. Citi Bike relies on manual orchestrations of rebalancing bikes between dispatchers and field agents. Motivated by such problem and the lack of smart autonomous solutions in this area, this project explored a new RL architecture called Distributed RL (DiRL) with Transfer Learning (TL) capability. The DiRL solution is adaptive to changing traffic dynamics when keeping bike stock under control at the minimum cost. DiRL achieved a 350% improvement in bike rebalancing autonomously and TL offered a 62.4% performance boost in managing an entire bike network. Lastly, a field trip to the dispatch office of Chariot, a ride-sharing service, provided insights to overcome challenges of deploying an RL solution in the real world.