عنوان انگلیسی مقاله:
An actor-critic deep reinforcement learning approach for metro train scheduling with rolling stock circulation under stochastic demand
ترجمه فارسی عنوان مقاله:
یک رویکرد یادگیری تقویتی عمیق بازیگر منتقد برای زمانبندی قطارهای مترو با گردش موجودی کالا تحت تقاضای تصادفی
Sciencedirect - Elsevier - Transportation Research Part B 140 (2020) 210–235
Cheng-shuo Ying a , Andy H.F. Chow b , ∗, Kwai-Sang Chin a
This paper presents a novel actor-critic deep reinforcement learning approach for metro train scheduling with circulation of limited rolling stock. The scheduling problem is mod- eled as a Markov decision process driven by stochastic passenger demand. As in most dy- namic optimization problems, the complexity of the scheduling process grows exponen- tially with the amount of states, decisions, and uncertainties involved. This study aims to address this ‘curses of dimensionality’ issue by adopting an actor-critic deep reinforce- ment learning solution framework. The framework simplifies the evaluation and searching process for potential optimal solutions by parameterizing the original state and decision spaces with the use of artificial neural networks. A deep deterministic policy gradient al- gorithm is developed for training the artificial neural networks via simulated system tran- sitions before the actor-critic agent can be applied for online schedule control. The pro- posed approach is tested with a real-world scenario configured with data collected from the Victoria Line of London Underground, UK. Experiment results illustrate the advantages of the proposed method over a range of established meta-heuristics in terms of comput- ing time, system efficiency, and robustness under different stochastic environments. This study innovates urban transit operations with state-of-the-art computer science and dy- namic optimization techniques.
Keywords: Metro train scheduling | Stochastic transit demand | Actor-critic architecture | Deep reinforcement learning | Multi-objective optimization