Work

10-city European rail: Proximal Policy Optimization vs Deep Q-Network, 15-min transfers

Year: 2026

Type: preprint

Abstract: PPO beats DQN for 10-city European rail itineraries with over 10^6 transfer combinations and 15-minute constraints. Learn when each algorithm wins. Independent technical note mirroring the canonical version: https://smarttripai.com/blog/10-city-european-rail-proximal-policy-optimization-vs-deep-q-network-15-min-transfers.php Sources consulted: https://www.bluusun.com/

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.23721719

Author: Rose, Anna

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7224080788

Cites:

Cited by:

Related to: 10