pith. sign in

arxiv: 2606.23257 · v1 · pith:5PWGZOPSnew · submitted 2026-06-22 · 💻 cs.LG · cs.AI· math.OC

Dynamic multi-agent deep reinforcement learning-based pricing and incentivization approach in multimodal transportation networks

Khadidja Kadem , Mostafa Ameli , Carlos Lima Azevedo , Mahdi Zargayouna , Latifa Oukhellou This is my paper

Pith reviewed 2026-06-26 09:11 UTC · model grok-4.3

classification 💻 cs.LG cs.AImath.OC
keywords multi-agent reinforcement learningdynamic pricingincentivizationmultimodal transportationshared mobility servicespublic transportcongestion managementemissions reduction
0
0 comments X

The pith

A multi-agent deep reinforcement learning framework coordinates dynamic pricing for shared mobility services and incentives for public transport to reduce costs and emissions while increasing profits and equity.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes a multi-agent deep reinforcement learning approach for multimodal transportation where one agent manages public transport incentives for better equity and lower emissions while another adjusts shared mobility fares for revenue. The agents interact with the system and learn strategies that respond to demand and congestion changes. In simulations of a morning peak period, this leads to lower congestion, reduced traveler costs by around 20 percent, emissions down by 10 percent, and nearly double the public transport profit. The setup helps balance the goals of authorities, providers, and users in one coordinated system. This matters because it offers a way to manage conflicting interests in complex transport networks without manual rule setting.

Core claim

The multi-agent deep reinforcement learning framework integrates two agents that capture interactions through dynamic pricing and incentivization strategies for SMSs and public transport, adapt to evolving demand, congestion, and network conditions, and in numerical experiments over a three-hour morning peak period effectively reduce congestion peaks, lower commuters' costs by around 20% and emissions by approximately 10%, while nearly doubling public transport profit and supporting a more equitable distribution of benefits.

What carries the argument

Two reinforcement learning agents, one for the public authority allocating spatio-temporal incentives and one for the SMS provider dynamically adjusting fares, that interact with the transportation system.

If this is right

  • Congestion peaks are reduced during peak periods.
  • Commuter costs drop by around 20%.
  • Emissions fall by about 10%.
  • Public transport profit nearly doubles.
  • Benefits are distributed more equitably.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The framework could be used to simulate and test the impacts of various policy changes before implementing them in real cities.
  • Similar multi-agent reinforcement learning methods might coordinate stakeholders in other domains with conflicting goals, such as resource allocation in smart cities.
  • Validating the models with real traveler data would allow checking if the reported improvements hold outside the simulation.
  • Adding more agents for other mobility options could extend the coordination to larger systems.

Load-bearing premise

The simulated transportation system and traveler response model used in the experiments accurately represent real-world demand patterns, congestion dynamics, and behavioral responses to pricing and incentives.

What would settle it

Applying the pricing and incentivization strategies learned by the agents in an actual city network and finding no reduction in congestion peaks or commuter costs would show the approach does not deliver the claimed benefits.

Figures

Figures reproduced from arXiv: 2606.23257 by Carlos Lima Azevedo, Khadidja Kadem, Latifa Oukhellou, Mahdi Zargayouna, Mostafa Ameli.

Figure 1
Figure 1. Figure 1: Stakeholder interactions and feedback mechanisms in multimodal systems with SMSs [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Dynamic Modeling framework for multimodal transportation systems using rolling horizon [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: RL-based dynamic incentivization strategy by public authorities [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Multimodal trip-based macroscopic traffic simulator The road network is modeled with a trip-based MFD that represents individual trajectories while maintaining a simplified description of network dynamics (Lamotte and Geroliminis, 2018; Mariotte et al., 2017). It captures the dynamics of private vehicles, carpooling drivers, ridesharing service vehicles, and buses. Trips with a passenger role (RS, CP, bus,… view at source ↗
Figure 5
Figure 5. Figure 5: Sioux Falls network with PT infrastructure and heterogeneous user classes [PITH_FULL_IMAGE:figures/full_fig_p016_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Temporal evolution of average network speed under di [PITH_FULL_IMAGE:figures/full_fig_p018_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Distribution of average commuters’ gains and losses across departure times and user classes for : (1) [PITH_FULL_IMAGE:figures/full_fig_p020_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Spatial distribution of the Gini index across network nodes for the three incentivization scenarios. The Gini indices are measured for [PITH_FULL_IMAGE:figures/full_fig_p021_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: (a): Temporal evolution of average network speed. (b): Comparative analysis of the performance metrics for the simulated scenarios. [PITH_FULL_IMAGE:figures/full_fig_p022_9.png] view at source ↗
read the original abstract

In multimodal transportation systems, shared mobility services (SMSs) are promoted for their potential to enhance flexibility and reduce congestion. However, SMS demand is often concentrated in high-density areas, which can limit the effectiveness and accessibility for various commuter groups. This uneven integration challenges transportation system efficiency, especially in terms of emissions and spatial equity. Addressing these issues requires coordination among multiple stakeholders whose objectives frequently conflict. Whereas authorities aim to ensure sustainable and equitable mobility, SMS providers focus on revenue maximization, and travelers seek to minimize personal travel costs. This paper proposes a multi-agent deep reinforcement learning framework that captures these interactions through dynamic pricing and incentivization strategies for SMSs and public transport. The framework integrates two reinforcement learning (RL) agents: (i) a public authority that allocates spatio-temporal public transport incentives to improve equity, emissions, and efficiency, and (ii) an SMS provider that dynamically adjusts fares to optimize revenue. The agents interact with the transportation system and adapt strategies in response to evolving demand, congestion, and network conditions. Numerical experiments conducted over a three-hour morning peak period show that dynamic incentivization effectively reduces congestion peaks, lowers commuters' costs by around 20% and emissions by approximately 10%, while nearly doubling public transport profit and supporting a more equitable distribution of benefits. When combined with dynamic SMS pricing, the two RL agents demonstrate the ability to balance conflicting objectives between private providers and public authorities. The proposed approach provides a decision-support tool for sustainable and equitable multimodal mobility planning.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes a multi-agent deep reinforcement learning framework for coordinating dynamic pricing by shared mobility service (SMS) providers and spatio-temporal incentivization by public authorities in multimodal transportation networks. Two RL agents interact with an agent-based simulator: one optimizes SMS fares for revenue, the other allocates incentives to improve equity, emissions, and system efficiency. Numerical experiments over a three-hour morning peak period report that the approach reduces congestion peaks, lowers commuter costs by around 20%, cuts emissions by approximately 10%, nearly doubles public transport profit, and improves equity; combining both agents balances stakeholder objectives.

Significance. If the experimental claims hold under validated conditions, the work could supply a practical decision-support tool for balancing revenue, sustainability, and equity goals in multimodal systems via adaptive RL agents. The multi-agent formulation directly addresses conflicting objectives among authorities, providers, and travelers, which is a relevant direction for transportation optimization. No machine-checked proofs, open code, or parameter-free derivations are described.

major comments (2)
  1. [Abstract and Numerical Experiments] Abstract and Numerical Experiments section: the central quantitative claims (commuter costs reduced by ~20%, emissions by ~10%, public transport profit nearly doubled) rest on an internally generated synthetic demand model whose origin-destination matrix, mode-choice probabilities, congestion functions, and behavioral elasticities are not calibrated to observed counts or revealed-preference data. No calibration metrics, hold-out validation, sensitivity analysis over key parameters, or comparison against real-world network topology are supplied, so the reported deltas cannot be distinguished from artifacts of the chosen functional forms.
  2. [Abstract and Numerical Experiments] Abstract and Numerical Experiments section: the experiments supply no information on simulation setup details (network size, demand generation procedure, baseline policies, number of runs, error bars, or statistical significance tests), making it impossible to assess whether the reported improvements are robust or reproducible.
minor comments (1)
  1. [Abstract] Abstract: the description of the two RL agents would be clearer if the specific deep RL algorithms (e.g., DQN, PPO, or actor-critic variants) and state/action spaces were named.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive comments on the experimental claims and setup. We address each point below and will revise the manuscript accordingly to improve transparency and clarify the scope of the numerical results.

read point-by-point responses

  1. Referee: [Abstract and Numerical Experiments] Abstract and Numerical Experiments section: the central quantitative claims (commuter costs reduced by ~20%, emissions by ~10%, public transport profit nearly doubled) rest on an internally generated synthetic demand model whose origin-destination matrix, mode-choice probabilities, congestion functions, and behavioral elasticities are not calibrated to observed counts or revealed-preference data. No calibration metrics, hold-out validation, sensitivity analysis over key parameters, or comparison against real-world network topology are supplied, so the reported deltas cannot be distinguished from artifacts of the chosen functional forms.

    Authors: We agree that the demand model is fully synthetic and has not been calibrated against real-world counts or revealed-preference data. This design choice was made to enable controlled, reproducible experiments that isolate the impact of the multi-agent RL policies under varying congestion and equity conditions. We acknowledge that the reported percentage improvements are therefore illustrative rather than predictive of any specific city. In the revised manuscript we will (i) add an explicit Limitations subsection stating the synthetic nature of the demand model, (ii) include a sensitivity analysis over the main behavioral elasticities and congestion parameters, and (iii) clarify that future work will seek calibration with observed data. These changes will prevent readers from over-generalizing the numerical deltas. revision: yes

  2. Referee: [Abstract and Numerical Experiments] Abstract and Numerical Experiments section: the experiments supply no information on simulation setup details (network size, demand generation procedure, baseline policies, number of runs, error bars, or statistical significance tests), making it impossible to assess whether the reported improvements are robust or reproducible.

    Authors: We apologize for the omission of these implementation details. The revised manuscript will contain a new subsection (likely 4.1 or 4.2) that reports: network topology (number of nodes, links, and zones), the exact procedure used to generate the synthetic origin-destination matrix and time-varying demand, the baseline policies against which the RL agents are compared, the number of independent simulation runs performed, the presence of error bars or confidence intervals on all reported figures, and the statistical tests (e.g., paired t-tests) used to assess significance of the observed differences. We believe these additions will allow readers to evaluate reproducibility. revision: yes

Circularity Check

0 steps flagged

No circularity detected; simulation results do not reduce to self-referential inputs by construction.

full rationale

The paper describes a multi-agent RL framework for dynamic pricing and incentives, then reports outcomes from numerical experiments on a three-hour peak period. No derivation chain, equations, or parameter-fitting steps are presented that would make the reported 20% cost reduction, 10% emissions drop, or doubled PT profit equivalent to the model's own inputs by definition. The results are generated by running the proposed agents inside a simulator; this is standard empirical evaluation rather than a fitted-input-called-prediction or self-definitional loop. No self-citation is invoked as a uniqueness theorem or load-bearing premise. The paper is therefore self-contained against the circularity criteria, with the quantitative claims resting on the simulator's behavior rather than on any internal algebraic identity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract supplies no information on free parameters, background axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5825 in / 1201 out tokens · 32054 ms · 2026-06-26T09:11:38.521672+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

299 extracted references · 244 canonical work pages · 4 internal anchors

  1. [1]

    Transportation Research Record: Journal of the Transportation Research Board , author =

    Optimizing. Transportation Research Record: Journal of the Transportation Research Board , author =. 2021 , pages =. doi:10.1177/03611981211025512 , abstract =

    work page doi:10.1177/03611981211025512 2021

  2. [2]

    Transportation Research Part C: Emerging Technologies , author =

    Personalized incentives for promoting sustainable travel behaviors , volume =. Transportation Research Part C: Emerging Technologies , author =. 2020 , keywords =. doi:10.1016/j.trc.2019.05.015 , abstract =

    work page doi:10.1016/j.trc.2019.05.015 2020

  3. [3]

    Transport Policy , author =

    The effects of public transport subsidies for lower-income users on public transport use:. Transport Policy , author =. 2022 , keywords =. doi:10.1016/j.tranpol.2022.07.016 , abstract =

    work page doi:10.1016/j.tranpol.2022.07.016 2022

  4. [4]

    Mathematics , author =

    A. Mathematics , author =. 2025 , note =. doi:10.3390/math13111738 , abstract =

    work page doi:10.3390/math13111738 2025

  5. [5]

    The 15-Minute City Dilemma?

    The potential of governmental regulation on shared mobility-on-demand systems , volume =. Transportation Research Part A: Policy and Practice , author =. 2025 , pages =. doi:10.1016/j.tra.2024.104360 , abstract =

    work page doi:10.1016/j.tra.2024.104360 2025

  6. [6]

    Transportation Research Part C: Emerging Technologies , author =

    Regulating mobility-on-demand services:. Transportation Research Part C: Emerging Technologies , author =. 2021 , pages =. doi:10.1016/j.trc.2021.103075 , abstract =

    work page doi:10.1016/j.trc.2021.103075 2021

  7. [7]

    Zardini, Gioele and Lanzetti, Nicolas and Guerrini, Laura and Frazzoli, Emilio and Dörfler, Florian , month = sep, year =. Game. 2021. doi:10.1109/ITSC48978.2021.9564501 , abstract =

    work page doi:10.1109/itsc48978.2021.9564501 2021

  8. [8]

    Gerstgrasser, Matthias and Parkes, David C , year =. Meta-

  9. [9]

    Nekoei, Hadi and Badrinaaraayanan, Akilesh and Sinha, Amit and Amini, Mohammad and Rajendran, Janarthanan and Mahajan, Aditya and Chandar, Sarath , year =. Dealing. 2nd

  10. [10]

    Nekoei, Hadi and Badrinaaraayanan, Akilesh and Sinha, Amit and Amini, Mohammad and Rajendran, Janarthanan and Mahajan, Aditya and Chandar, Sarath , year =

  11. [11]

    Transportation Research Part C: Emerging Technologies , author =

    Personalised incentives for demand management of congested public transport systems:. Transportation Research Part C: Emerging Technologies , author =. 2026 , keywords =. doi:10.1016/j.trc.2026.105566 , abstract =

    work page doi:10.1016/j.trc.2026.105566 2026

  12. [12]

    OECD Net Zero+ Policy Papers , author =

    Unlocking the potential of demand-side climate mitigation strategies , url =. OECD Net Zero+ Policy Papers , author =

  13. [13]

    European Commission: Mobility and Transport , author =

    Sustainable & smart. European Commission: Mobility and Transport , author =

  14. [14]

    OECD Publishing , author =

  15. [15]

    OECD Publishing , author =

    Regulating. OECD Publishing , author =

  16. [16]

    ITF Research Reports , author =

    Sustainable. ITF Research Reports , author =

  17. [17]

    OECD Publishing , author =

    How. OECD Publishing , author =

  18. [18]

    European Commission , year =. Road

  19. [19]

    Finding the. Manage. Sci. , author =. 1971 , pages =. doi:10.1287/mnsc.17.11.712 , abstract =

    work page doi:10.1287/mnsc.17.11.712 1971

  20. [20]

    Transportation Research Part D: Transport and Environment , author =

    Deep learning approach to predict microscopic pollutant emissions from mesoscopic traffic simulations , volume =. Transportation Research Part D: Transport and Environment , author =. 2025 , keywords =. doi:10.1016/j.trd.2025.104791 , abstract =

    work page doi:10.1016/j.trd.2025.104791 2025

  21. [21]

    Transportation Research Record: Journal of the Transportation Research Board , author =

    Integrating. Transportation Research Record: Journal of the Transportation Research Board , author =. 2016 , pages =. doi:10.3141/2597-03 , abstract =

    work page doi:10.3141/2597-03 2016

  22. [22]

    Transportation Research Part A: Policy and Practice , author =

    Exploring travelers’ responses to a prepeak discount fare policy and optimizing the pricing strategy to ease peak congestion:. Transportation Research Part A: Policy and Practice , author =. 2025 , keywords =. doi:10.1016/j.tra.2024.104335 , abstract =

    work page doi:10.1016/j.tra.2024.104335 2025

  23. [23]

    Transportation Planning and Technology , author =

    Ride-pooling adoption, efficiency and level of service under alternative demand, behavioural and pricing settings , volume =. Transportation Planning and Technology , author =. 2023 , note =. doi:10.1080/03081060.2023.2194874 , abstract =

    work page doi:10.1080/03081060.2023.2194874 2023

  24. [24]

    Cities , author =

    Simulating impacts of. Cities , author =. 2021 , keywords =. doi:10.1016/j.cities.2021.103345 , abstract =

    work page doi:10.1016/j.cities.2021.103345 2021

  25. [25]

    Transportation Research Record: Journal of the Transportation Research Board , author =

    Estimation of. Transportation Research Record: Journal of the Transportation Research Board , author =. 2024 , pages =. doi:10.1177/03611981231223752 , abstract =

    work page doi:10.1177/03611981231223752 2024

  26. [26]

    Transportation Research Part A: Policy and Practice , author =

    Quantifying the employment accessibility benefits of shared automated vehicle mobility services:. Transportation Research Part A: Policy and Practice , author =. 2020 , keywords =. doi:10.1016/j.tra.2020.09.002 , abstract =

    work page doi:10.1016/j.tra.2020.09.002 2020

  27. [27]

    Transportation Research Part A: Policy and Practice , author =

    Who benefits from. Transportation Research Part A: Policy and Practice , author =. 2021 , keywords =. doi:10.1016/j.tra.2021.09.013 , abstract =

    work page doi:10.1016/j.tra.2021.09.013 2021

  28. [28]

    Transportation Research Part C: Emerging Technologies , author =

    Transit-oriented autonomous vehicle operation with integrated demand-supply interaction , volume =. Transportation Research Part C: Emerging Technologies , author =. 2018 , keywords =. doi:10.1016/j.trc.2018.10.018 , abstract =

    work page doi:10.1016/j.trc.2018.10.018 2018

  29. [29]

    Transportation Research Part E: Logistics and Transportation Review , author =

    Regulating the ride-hailing market in the age of uberization , volume =. Transportation Research Part E: Logistics and Transportation Review , author =. 2023 , keywords =. doi:10.1016/j.tre.2022.102969 , abstract =

    work page doi:10.1016/j.tre.2022.102969 2023

  30. [30]

    Transportation Research Part A: Policy and Practice , author =

    Optimal fare and fleet size regulation in a taxi/ride-sourcing market with congestion effects, emission externalities, and gasoline/electric vehicles , volume =. Transportation Research Part A: Policy and Practice , author =. 2022 , keywords =. doi:10.1016/j.tra.2021.12.012 , abstract =

    work page doi:10.1016/j.tra.2021.12.012 2022

  31. [31]

    Transportation Research Part C: Emerging Technologies , author =

    Economic analysis of ride-sourcing markets , volume =. Transportation Research Part C: Emerging Technologies , author =. 2016 , keywords =. doi:10.1016/j.trc.2016.07.010 , abstract =

    work page doi:10.1016/j.trc.2016.07.010 2016

  32. [32]

    Transportation Research Part B: Methodological , author =

    Competition and third-party platform-integration in ride-sourcing markets , volume =. Transportation Research Part B: Methodological , author =. 2022 , keywords =. doi:10.1016/j.trb.2021.08.002 , abstract =

    work page doi:10.1016/j.trb.2021.08.002 2022

  33. [33]

    Transportation Research Part C: Emerging Technologies , author =

    Dynamic pricing and penalty strategies in a coupled market with ridesourcing service and taxi considering time-dependent order cancellation behaviour , volume =. Transportation Research Part C: Emerging Technologies , author =. 2022 , keywords =. doi:10.1016/j.trc.2022.103621 , abstract =

    work page doi:10.1016/j.trc.2022.103621 2022

  34. [34]

    Transportation Research Part C: Emerging Technologies , author =

    Spatio-temporal pricing algorithm for ride-hailing platforms where drivers can decline ride requests , volume =. Transportation Research Part C: Emerging Technologies , author =. 2023 , keywords =. doi:10.1016/j.trc.2023.104200 , abstract =

    work page doi:10.1016/j.trc.2023.104200 2023

  35. [35]

    European Journal of Operational Research , author =

    Optimal pricing for ride-sourcing platforms , volume =. European Journal of Operational Research , author =. 2019 , keywords =. doi:10.1016/j.ejor.2019.04.044 , abstract =

    work page doi:10.1016/j.ejor.2019.04.044 2019

  36. [36]

    Transportation Research Part C: Emerging Technologies , author =

    A hierarchical control framework for vehicle repositioning in ride-hailing systems , volume =. Transportation Research Part C: Emerging Technologies , author =. 2024 , keywords =. doi:10.1016/j.trc.2024.104717 , abstract =

    work page doi:10.1016/j.trc.2024.104717 2024

  37. [37]

    Transportation Research Part C: Emerging Technologies , author =

    Real-world ride-hailing vehicle repositioning using deep reinforcement learning , volume =. Transportation Research Part C: Emerging Technologies , author =. 2021 , keywords =. doi:10.1016/j.trc.2021.103289 , abstract =

    work page doi:10.1016/j.trc.2021.103289 2021

  38. [38]

    Efficient

    Li, Minne and Qin, Zhiwei and Jiao, Yan and Yang, Yaodong and Wang, Jun and Wang, Chenxi and Wu, Guobin and Ye, Jieping , year =. Efficient. The. doi:10.1145/3308558.3313433 , abstract =

    work page doi:10.1145/3308558.3313433

  39. [39]

    Transportmetrica B: Transport Dynamics , author =

    A stochastic evolutionary dynamic game model for analyzing the ride-sourcing market with limited platform reputation , volume =. Transportmetrica B: Transport Dynamics , author =. 2023 , note =. doi:10.1080/21680566.2023.2248399 , abstract =

    work page doi:10.1080/21680566.2023.2248399 2023

  40. [41]

    Networks , author =

    The network equilibrium problem in integers , volume =. Networks , author =. 1973 , pages =. doi:10.1002/net.3230030104 , abstract =

    work page doi:10.1002/net.3230030104 1973

  41. [42]

    Journal of Social Issues , author =

    Travel. Journal of Social Issues , author =. 2007 , pages =. doi:10.1111/j.1540-4560.2007.00500.x , abstract =

    work page doi:10.1111/j.1540-4560.2007.00500.x 2007

  42. [43]

    Gurobi Optimization, LLC , year =. Gurobi

  43. [44]

    Sustainable Development , author =

    The smart future for sustainable development:. Sustainable Development , author =. 2025 , keywords =. doi:10.1002/sd.3131 , abstract =

    work page doi:10.1002/sd.3131 2025

  44. [45]

    Proceedings of the Institute of Civil Engineers, Part II , author =

    Some. Proceedings of the Institute of Civil Engineers, Part II , author =. 1952 , pages =. doi:10.1680/ipeds.1952.11362 , language =

    work page doi:10.1680/ipeds.1952.11362 1952

  45. [46]

    IEEE Transactions on Intelligent Transportation Systems , author =

    Multi-. IEEE Transactions on Intelligent Transportation Systems , author =. 2023 , pages =. doi:10.1109/TITS.2023.3302014 , abstract =

    work page doi:10.1109/tits.2023.3302014 2023

  46. [47]

    Journal of Advanced Transportation , author =

    Macroscopic. Journal of Advanced Transportation , author =. 2020 , note =. doi:10.1155/2020/4951953 , abstract =

    work page doi:10.1155/2020/4951953 2020

  47. [48]

    Transportation Research Part C: Emerging Technologies , author =

    Leveraging ride-hailing services for social good:. Transportation Research Part C: Emerging Technologies , author =. 2023 , pages =. doi:10.1016/j.trc.2023.104284 , abstract =

    work page doi:10.1016/j.trc.2023.104284 2023

  48. [49]

    World Transport Policy & Practice , author =

    Evaluating. World Transport Policy & Practice , author =. 2017 , pages =

    2017

  49. [50]

    Transportation Research Part A: Policy and Practice , author =

    Equity in network design and pricing:. Transportation Research Part A: Policy and Practice , author =. 2023 , keywords =. doi:10.1016/j.tra.2023.103800 , abstract =

    work page doi:10.1016/j.tra.2023.103800 2023

  50. [51]

    Transportation Research Part C: Emerging Technologies , author =

    Dynamic tradable credit scheme for multimodal urban networks , volume =. Transportation Research Part C: Emerging Technologies , author =. 2023 , keywords =. doi:10.1016/j.trc.2023.104061 , abstract =

    work page doi:10.1016/j.trc.2023.104061 2023

  51. [52]

    Annals of Operations Research , author =

    Adaptive forecast-driven repositioning for dynamic ride-sharing , issn =. Annals of Operations Research , author =. doi:10.1007/s10479-022-04560-3 , abstract =

    work page doi:10.1007/s10479-022-04560-3

  52. [53]

    Manufacturing & Service Operations Management , author =

    The. Manufacturing & Service Operations Management , author =. 2017 , note =. doi:10.1287/msom.2017.0618 , abstract =

    work page doi:10.1287/msom.2017.0618 2017

  53. [54]

    Numerical optimization , publisher =

    nocedal, Jorge and Wright, Stephen J , year =. Numerical optimization , publisher =

  54. [55]

    Transportation

    Stabler, Ben and Bar-Gera, Hillel and Sall, Elizabeth , year =. Transportation

  55. [56]

    IEEE Access , author =

    Efficient. IEEE Access , author =. 2019 , keywords =. doi:10.1109/ACCESS.2019.2942497 , abstract =

    work page doi:10.1109/access.2019.2942497 2019

  56. [57]

    Multimodal Transportation , author =

    A meso-to-macro cross-resolution performance approach for connecting polynomial arrival queue model to volume-delay function with inflow demand-to-capacity ratio , volume =. Multimodal Transportation , author =. 2022 , keywords =. doi:10.1016/j.multra.2022.100017 , abstract =

    work page doi:10.1016/j.multra.2022.100017 2022

  57. [58]

    Urban planning division , institution =

    US DoC , year =. Urban planning division , institution =

  58. [59]

    Studies in the

    Beckmann, Martin and McGuire, Charles B and Winsten, Christopher B , year =. Studies in the

  59. [60]

    Transportation Research Interdisciplinary Perspectives , author =

    How realistic is static traffic assignment?. Transportation Research Interdisciplinary Perspectives , author =. 2021 , keywords =. doi:10.1016/j.trip.2021.100320 , abstract =

    work page doi:10.1016/j.trip.2021.100320 2021

  60. [61]

    Transportation Research Interdisciplinary Perspectives , author =

    Multimodal transport route selection:. Transportation Research Interdisciplinary Perspectives , author =. 2024 , keywords =. doi:10.1016/j.trip.2024.101252 , abstract =

    work page doi:10.1016/j.trip.2024.101252 2024

  61. [62]

    and Verhoef, Erik T

    Small, Kenneth A. and Verhoef, Erik T. and Lindsey, Robin , month = jun, year =. The

  62. [63]

    Scientific Reports , author =

    Optimization of dynamic incentive strategies for public transportation based on reinforcement learning and network synergy effect , volume =. Scientific Reports , author =. 2025 , note =. doi:10.1038/s41598-025-16632-y , abstract =

    work page doi:10.1038/s41598-025-16632-y 2025

  63. [64]

    Guo, Qianwen and Lu, Jiaqing and Chow, Joseph Y. J. and Schonfeld, Paul , month = oct, year =. Equity-aware. doi:10.48550/arXiv.2502.08731 , abstract =

    work page doi:10.48550/arxiv.2502.08731

  64. [65]

    Transportation Research Part A: Policy and Practice , author =

    A multi-dimension and high-granularity equity measurement for transportation services through accessibility and reliability , volume =. Transportation Research Part A: Policy and Practice , author =. 2026 , keywords =. doi:10.1016/j.tra.2025.104729 , abstract =

    work page doi:10.1016/j.tra.2025.104729 2026

  65. [66]

    Transportation Research Part C: Emerging Technologies , author =

    Transit fares integrating alternative modes as a delay insurance , volume =. Transportation Research Part C: Emerging Technologies , author =. 2024 , keywords =. doi:10.1016/j.trc.2024.104745 , abstract =

    work page doi:10.1016/j.trc.2024.104745 2024

  66. [67]

    Transportmetrica B: Transport Dynamics , author =

    Day-to-day dynamics in two-sided ridesourcing markets , volume =. Transportmetrica B: Transport Dynamics , author =. 2025 , pages =. doi:10.1080/21680566.2024.2439987 , abstract =

    work page doi:10.1080/21680566.2024.2439987 2025

  67. [68]

    Journal of Transport & Health , author =

    Policy measures to reduce road congestion:. Journal of Transport & Health , author =. 2025 , keywords =. doi:10.1016/j.jth.2025.101984 , abstract =

    work page doi:10.1016/j.jth.2025.101984 2025

  68. [69]

    Transportation Research Part C: Emerging Technologies , author =

    A multi-agent reinforcement learning framework for integrated traffic signal control and dynamic bus lane access management , volume =. Transportation Research Part C: Emerging Technologies , author =. 2026 , keywords =. doi:10.1016/j.trc.2025.105391 , abstract =

    work page doi:10.1016/j.trc.2025.105391 2026

  69. [70]

    van Wee, Bert and Mouter, Niek , editor =. Chapter. Advances in. 2021 , doi =

    2021

  70. [71]

    Research in Transportation Economics , author =

    Part. Research in Transportation Economics , author =. 2010 , keywords =. doi:10.1016/j.retrec.2010.03.002 , abstract =

    work page doi:10.1016/j.retrec.2010.03.002 2010

  71. [72]

    Environment, Development and Sustainability , author =

    A forecast analysis on world population and urbanization process , volume =. Environment, Development and Sustainability , author =. 2008 , keywords =. doi:10.1007/s10668-007-9081-8 , abstract =

    work page doi:10.1007/s10668-007-9081-8 2008

  72. [73]

    Energy Policy , author =

    Meeting goals of sustainability policy:. Energy Policy , author =. 2020 , keywords =. doi:10.1016/j.enpol.2019.111210 , abstract =

    work page doi:10.1016/j.enpol.2019.111210 2020

  73. [74]

    Journal of Machine Learning Research , author =

    Stable-. Journal of Machine Learning Research , author =. 2021 , pages =

    2021

  74. [75]

    Reinforcement

    Caspi, Itai and Leibovich, Gal and Endrawis, Shadi and Novik, Gal , month = dec, year =. Reinforcement. doi:10.5281/ZENODO.1134899 , note =

    work page doi:10.5281/zenodo.1134899

  75. [76]

    Transportation Research Part C: Emerging Technologies , author =

    Assessing how ride-hailing rebalancing strategies improve the resilience of multi-modal transportation systems , volume =. Transportation Research Part C: Emerging Technologies , author =. 2025 , keywords =. doi:10.1016/j.trc.2025.105300 , abstract =

    work page doi:10.1016/j.trc.2025.105300 2025

  76. [77]

    Transportation , author =

    The critical role of the value of time in peer-to-peer ridesharing models , issn =. Transportation , author =. 2025 , keywords =. doi:10.1007/s11116-025-10677-8 , abstract =

    work page doi:10.1007/s11116-025-10677-8 2025

  77. [78]

    Transportation Research Part C: Emerging Technologies , author =

    Integrated operation of ride-hailing and shared micromobility services in multimodal transportation networks with public transit:. Transportation Research Part C: Emerging Technologies , author =. 2025 , keywords =. doi:10.1016/j.trc.2025.105340 , abstract =

    work page doi:10.1016/j.trc.2025.105340 2025

  78. [79]

    Haarnoja, Tuomas and Zhou, Aurick and Abbeel, Pieter and Levine, Sergey , month = aug, year =. Soft. doi:10.48550/arXiv.1801.01290 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1801.01290

  79. [80]

    Proximal Policy Optimization Algorithms

    Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg , month = aug, year =. Proximal. doi:10.48550/arXiv.1707.06347 , abstract =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1707.06347

  80. [81]

    Transportation , author =

    Exploring the dynamics of dynamic ride-sharing: insights from a sensitivity analysis with an agent-based simulation , issn =. Transportation , author =. 2024 , keywords =. doi:10.1007/s11116-024-10564-8 , abstract =

    work page doi:10.1007/s11116-024-10564-8 2024

Showing first 80 references.