A Differential Game Model on the U.K. Government and Zero-emission Vehicle Manufacturer: method of Deep Reinforcement Learning

Chuqing Xi

doi:10.54097/5hcceq23

Authors

Chuqing Xi

DOI:

https://doi.org/10.54097/5hcceq23

Keywords:

Dynamic Optimization, Differential Game, Deep Reinforcement Learning, Environmental Economics.

Abstract

In this paper, a model based on the Differential Game is constructed to solve out the optimized funding value to the Zero-emission Vehicles manufacturers' battery research for the U.K. government. Multi-Agent Deep Deterministic Policy Gradient, a Reinforcement Learning algorithm, is used to solve out the Feedback Nash Equilibria. The optimal model outcome is compared with the empirical data from 2016 to 2023 from Statista and solve out the optimal funding value for the future 12 years. Since the focus of the paper is seeking optimal solutions rather than predicting, we will analyse the action gap between the government and the optimal solutions. Through our analysis, we provide policymakers with actionable recommendations for maximising the effectiveness of government funding in driving innovation and the transition to sustainability. Our findings underscore the importance of strategic patience, an innovation ecosystem, and proactive engagement with the manufacturers on achieving optimal outcomes for the ZEV market and society.

Downloads

Download data is not yet available.

References

Watanabe, C., Wakabayashi, K., Miyazawa, T. Industrial dynamism and the creation of a “virtuous cycle” between R&D, market growth and price reduction: The case of photovoltaic power generation (PV) development in Japan[J]. Technovation, 2000, 20(6): 299-312.

Gu, X., Zhou, L., Ieromonachou, P. Subsidising an electric vehicle supply chain with imperfect information[J]. International Journal of Production Economics, 2019, 211: 82-97.

Cheng, Y., Yao, Z., Wang, X. Differential Game Analysis for Cooperation Models in Automotive Supply Chain Under Low-Carbon Emission Reduction Policies[C]. In: International Workshop on Frontiers in Algorithmics, Cham: Springer Nature Switzerland, 2023, 147-159.

Hu, R., Laurière, M. Recent developments in machine learning methods for stochastic control and games [DB/OL]. arXiv preprint, 2023, arXiv:2303.10257.

Wang, M., Wang, L., Yue, T. An Application of Continuous Deep Reinforcement Learning Approach to Pursuit-Evasion Differential Game[C]. 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 2019: 1150-1156.

Xu, C., Zhang, Y., Wang, W., Dong, L. Pursuit and evasion strategy of a differential game based on deep reinforcement learning[J]. Frontiers in Bioengineering and Biotechnology, 2022, 10: 827408.

Asgharnia, A., Schwartz, H., Atia, M. Learning deception using fuzzy multi-level reinforcement learning in a multi-defender one-invader differential game[J]. International Journal of Fuzzy Systems, 2022, 24(7): 3015-3038.

Luo, Q., Saigal, R. Dynamic multiagent incentive contracts: Existence, uniqueness, and implementation [J]. Mathematics, 2020.

Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I. Multi-agent actor-critic for mixed cooperative-competitive environments[C]. Advances in Neural Information Processing Systems, 2017, 30.

François-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J. An introduction to deep reinforcement learning[M]. Foundations and Trends in Machine Learning, 2018, 11(3-4): 219-354.

Zai, A., Brown, B. Deep reinforcement learning in action[M]. Manning Publications Co., 2020: P10-1.

GOV.UK. Vehicle licensing statistics: 2022[DB/OL]. Available at: https://www.gov.uk/government/statistics/vehicle-licensing-statistics-2022/vehicle-licensing-statistics-2022 [Accessed 2023].

Statista. Electric Vehicles – UK. Statista Market Forecast [DB/OL]. Available at: https://www.statista.com/outlook/mmo/electric-vehicles/united-kingdom?currency=usd#unit-sales [Accessed 2023].

Nair, S., Howlett, M. Policy myopia as a source of policy failure: Adaptation and policy learning under deep uncertainty[J]. Policy & Politics, 2017, 45(1): 103-118.