发表机构
School of Computer Science, University of Galway（戈尔韦大学计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究将光伏政策设计建模为序列决策问题，结合强化学习与基于智能体模型，通过PPO等算法学习不同权衡的政策，其生成的政策权衡结构清晰且优于静态基准，可用于不确定性下的自适应政策设计。
AI 中文摘要
设计有效且财政可持续的太阳能光伏（PV）推广政策，需在不确定性与异质性决策背景下平衡推广收益与公共支出。本研究将光伏政策设计建模为序列决策问题，将强化学习（RL）与随机基于智能体模型（ABM）相结合，该模型可模拟不确定性下的年度太阳能光伏推广情况。政策制定者智能体在16年的时间范围内选择年度激励措施，包括资本补贴、优惠贷款利率和上网电价。研究在标量化奖励框架内通过调整政策偏好，探究推广与成本间的权衡关系。采用PPO、SAC和TD3算法学习政策，并在随机模拟环境中进行评估。结果表明，该方法形成了清晰的权衡结构：最高推广量政策（TD3，成本权重$w_{\text{cost}}=0.5$）实现约4145个推广者，成本为4173万欧元；最低成本政策（PPO，$w_{\text{cost}}=2.0$）将支出降至727万欧元，对应2682个推广者；平衡政策（PPO，$w_{\text{cost}}=1.6$）实现3495个推广者，成本为2247万欧元。不同算法均呈现一致的权衡模式，表明推广与成本关系具有鲁棒性，且RL框架相比静态基准政策能探索更广泛的政策配置。这些发现证明RL可作为不确定性下自适应政策设计的灵活工具。
英文摘要
Designing effective and fiscally sustainable policies for solar photovoltaic (PV) adoption requires balancing adoption gains against public expenditure under uncertainty and heterogeneous decision-making. This study formulates PV policy design as a sequential decision problem and integrates reinforcement learning (RL) with a stochastic agent-based model (ABM) that simulates yearly solar PV adoption under uncertainty. A policymaker agent selects annual incentives, including capital grants, subsidised loan rates, and feed-in tariffs, over a 16-year horizon. Adoption--cost trade-offs are explored by varying policy preferences within a scalarised reward framework. Policies are learned using PPO, SAC, and TD3 and evaluated under stochastic simulation. The results show that this approach produces a clear trade-off structure: the highest-adoption policy (TD3, $w_{\text{cost}}=0.5$) achieves approximately 4,145 adopters at a cost of EUR 41.73 million, while the lowest-cost policy (PPO, $w_{\text{cost}}=2.0$) reduces expenditure to EUR 7.27 million with 2,682 adopters. The balanced policy (PPO, $w_{\text{cost}}=1.6$) achieves 3,495 adopters at a cost of EUR 22.47 million. Across algorithms, consistent trade-off patterns are observed, indicating robustness of the adoption--cost relationship. Compared with static baseline policies, the RL framework explores a broader range of policy configurations. These findings demonstrate the potential of RL as a flexible tool for adaptive policy design under uncertainty.
