NeurIPS · 2023
Anytime-Competitive Reinforcement Learning with Policy Prior
Advances in Neural Information Processing Systems
Can reinforcement learning enforce cost protection throughout an episode?
ACRL constrains cumulative costs relative to a policy prior at each round, rather than only in expectation over episodes. The analysis establishes cost guarantees and regret relative to the constrained optimum, with experiments in carbon aware computing.
Research themes
Cite this paper
Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren. Anytime-Competitive Reinforcement Learning with Policy Prior. Advances in Neural Information Processing Systems, 2023. https://papers.nips.cc/paper_files/paper/2023/hash/f53437debdd397c42929d929614bc705-Abstract-Conference.html
BibTeX
@inproceedings{tongxin-anytime-rl,
title = {{Anytime-Competitive Reinforcement Learning with Policy Prior}},
author = {Jianyi Yang and Pengfei Li and Tongxin Li and Adam Wierman and Shaolei Ren},
year = {2023},
booktitle = {Advances in Neural Information Processing Systems},
url = {https://papers.nips.cc/paper\_files/paper/2023/hash/f53437debdd397c42929d929614bc705-Abstract-Conference.html}
}
Related papers
Counterfactual load forecasting with LLM-structured events and representation learning
NACF turns news into structured treatments and estimates load trajectories under alternative event conditions. Reweighting and representation balancing address observed confounding. Experiments examine factual accuracy and interpretable demand perturbations without claiming that unobserved counterfactual outcomes can be directly validated.
Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners
A measure of advice quality connects simulators and payoff predictions to strategic performance. The paper establishes benefits of reliable advice for approximate Stackelberg play and limitations on simultaneously exploiting accurate advice and protecting against inaccurate advice.
PEARL: A Physics-Enhanced Adaptive Residual Learning Framework for PV Modeling
PEARL separates a physical photovoltaic simulator from a learned residual correction. A controlled benchmark compares several machine learning architectures and a coupled modeling baseline, examining accuracy while retaining the physical model as an interpretable reference.