AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems

Yi Ma, Xiaotian Hao, Jianye HAO, Jiawen Lu, Xing Liu, Xialiang Tong, Mingxuan Yuan, Zhigang Li, Jie Tang, Zhaopeng Meng

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 49 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace fixed 10-min interval partition with upper-level RL agent (ablation)hierarchical RL with lower-level RL · DPDP 300-1objective (avg distance, km): 126.95 -> 122.42Improved
replace fixed interval partition with upper-level RL agent (ablation)hierarchical RL · DPDP 300-2objective (avg distance, km): 154.39 -> 142.33Improved
replace random operator selection with lower-level RL policy (ablation)10min-Interval · DPDP 300-1objective (avg distance, km): 139.16 -> 126.95Improved
replace random operator selection with lower-level RL policy (ablation)10min-Interval · DPDP 300-2objective (avg distance, km): 166.31 -> 154.39Improved
train on 300-order data instead of 1000-order data (ablation)hierarchical RL · DPDP 1000-1objective (avg distance, km): 159.18 -> 170.78Hurt
use full hierarchical RL instead of GreedyGreedy · DPDP 300-1objective (avg distance, km): 147.78 -> 122.42Improved
use full hierarchical RL instead of 1order-Interval E2ERLE2ERL · DPDP 300-1objective (avg distance, km): 158.39 -> 122.42Improved
use lower-level RL instead of ALNS on static PDPALNS · Static PDP 50-1solve time: 10728.34s -> 1459.23sImproved
use lower-level RL instead of ALNS on static PDPALNS · Static PDP 50-1objective (avg distance, km): 96.98 -> 82.43Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy