A Dual-Positive Monotone Parameterization for Multi-Segment Bids and a Validity Assessment Framework for Reinforcement Learning Agent-based Simulation of Electricity Markets

TL;DR

This paper introduces a novel parameterization for multi-segment bids in reinforcement learning-based electricity market simulations, ensuring better mathematical properties and providing a framework to assess the validity of simulation outcomes.

Contribution

It proposes a dual-positive monotone parameterization method for multi-segment bids and develops a validity assessment framework for RL-ABS in electricity markets.

Findings

The new parameterization maintains monotonicity and differentiability.

The validity framework improves the credibility of simulation results.

Enhanced bid modeling leads to more accurate market mechanism analysis.

Abstract

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...