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

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.