Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10252 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915933107257344 |
|---|---|
| author | Xu, Zunnan Jing, Zhaoxia Pan, Zhanhua |
| author_facet | Xu, Zunnan Jing, Zhaoxia Pan, Zhanhua |
| contents | Reinforcement learning agent-based simulation (RL-ABS) has become an important tool for electricity market mechanism analysis and evaluation. In the modeling of monotone, bounded, multi-segment stepwise bids, existing methods typically let the policy network first output an unconstrained action and then convert it into a feasible bid curve satisfying monotonicity and boundedness through post-processing mappings such as sorting, clipping, or projection. However, such post-processing mappings often fail to satisfy continuous differentiability, injectivity, and invertibility at boundaries or kinks, thereby causing gradient distortion and leading to spurious convergence in simulation results. Meanwhile, most existing studies conduct mechanism analysis and evaluation mainly on the basis of training-curve convergence, without rigorously assessing the distance between the simulation outcomes and Nash equilibrium, which severely undermines the credibility of the results. To address these issues, this paper proposes... |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10252 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Dual-Positive Monotone Parameterization for Multi-Segment Bids and a Validity Assessment Framework for Reinforcement Learning Agent-based Simulation of Electricity Markets Xu, Zunnan Jing, Zhaoxia Pan, Zhanhua Artificial Intelligence Systems and Control Reinforcement learning agent-based simulation (RL-ABS) has become an important tool for electricity market mechanism analysis and evaluation. In the modeling of monotone, bounded, multi-segment stepwise bids, existing methods typically let the policy network first output an unconstrained action and then convert it into a feasible bid curve satisfying monotonicity and boundedness through post-processing mappings such as sorting, clipping, or projection. However, such post-processing mappings often fail to satisfy continuous differentiability, injectivity, and invertibility at boundaries or kinks, thereby causing gradient distortion and leading to spurious convergence in simulation results. Meanwhile, most existing studies conduct mechanism analysis and evaluation mainly on the basis of training-curve convergence, without rigorously assessing the distance between the simulation outcomes and Nash equilibrium, which severely undermines the credibility of the results. To address these issues, this paper proposes... |
| title | A Dual-Positive Monotone Parameterization for Multi-Segment Bids and a Validity Assessment Framework for Reinforcement Learning Agent-based Simulation of Electricity Markets |
| topic | Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2604.10252 |