Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
Artificial Intelligence
2025-12-16 v1 Machine Learning
Abstract
In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here, we assess the robustness of RPI's empirical performance on two classical control tasks -- CartPole and Inverted Pendulum -- under changes to neural network and environmental parameters. Relative to DQN, Double DQN, DDPG, TD3, and PPO, RPI reaches near-optimal performance early and sustains this policy as training proceeds. Because deep RL methods are often hampered by sample inefficiency, training instability, and hyperparameter sensitivity, our results highlight RPI's promise as a more reliable alternative.
Cite
@article{arxiv.2512.12088,
title = {Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations},
author = {S. R. Eshwar and Aniruddha Mukherjee and Kintan Saha and Krishna Agarwal and Gugan Thoppe and Aditya Gopalan and Gal Dalal},
journal= {arXiv preprint arXiv:2512.12088},
year = {2025}
}