Log In Sign Up

A Distributed Reinforcement Learning Solution With Knowledge Transfer Capability for A Bike Rebalancing Problem

by   Ian Xiao, et al.

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 62.4 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.


page 10

page 12

page 14

page 21


Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems

Reinforcement learning (RL) has been used in a range of simulated real-w...

Transfer Learning in Deep Reinforcement Learning: A Survey

This paper surveys the field of transfer learning in the problem setting...

Reinforcement Learning from Simulation to Real World Autonomous Driving using Digital Twin

Reinforcement learning (RL) is a promising solution for autonomous vehic...

Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization

In recent years, Multifactorial Optimization (MFO) has gained a notable ...

A Bibliometric Analysis and Review on Reinforcement Learning for Transportation Applications

Transportation is the backbone of the economy and urban development. Imp...

Adaptive Energy Management for Real Driving Conditions via Transfer Reinforcement Learning

This article proposes a transfer reinforcement learning (RL) based adapt...