MInTRL (Minimal Intervention Reinforcement Learning) expands exploration in on-policy reinforcement learning by inserting sparse, local corrections into rollouts via a judge-intervention policy. These interventions replace erroneous suffixes and immediately return control to the main policy, allowing the agent to explore beyond its natural trajectory while maintaining on-policy data. The method uses a sequence-level advantage-regression objective, avoiding importance sampling, and demonstrates superior performance on math and code benchmarks compared to standard on-policy and off-policy baselines.
By Mingyu Chen, Yefan Tao, Gerald Friedland, Xuezhou Zhang, Chris Kong
arXiv:2606. 24160v1 Announce Type: new Abstract: Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.
By Elias Bareinboim, Junzhe Zhang, Sanghack Lee
arXiv:2609.14124v1 Announce Type: cross
Abstract: Medical image analysis is often hindered by biased datasets, which can lead to biased models and limited clinical applicability. A promising strategy...
By Yasin Ibrahim, Robin J. Evans, Konstantinos Kamnitsas
arXiv:2607. 27905v1 Announce Type: new Abstract: Counterfactual explanations (CFEs) enhance the interpretability of black-box models by generating alternative instances with adjusted feature values that achieve a contrastive outcome.
By Muhammad Adil Saleem, Syed Ali Raza, Mary-Anne Williams
Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i. e.
arXiv:2609.23753v1 Announce Type: cross
Abstract: Generative world models aim to predict future states conditioned on actions, where action controllability is fundamental for reliable dynamics modeli...
By Yikun Miao, Fangqi Zhu, Quanxin Shou, Xiaoyi Pang, Zhengyang Yan, Junhao Li, Haodong Wang, Zicong Hong, Song Guo
Counterfactual explanations (CFEs) enhance the interpretability of black-box models by generating alternative instances with adjusted feature values that achieve a contrastive outcome. Reinforcement learning (RL) offers a promising approach for CFE generation, enabling efficient exploration of counterfactual instances while ensuring control over key metrics like validity, sparsity, and proximity.
arXiv:2608.20909v1 Announce Type: new
Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
By Xuyao Lin, Yixiang Shan, Jinru Duan, Tao Yang, Xinyu Zhao, Runyu Lei, Yiming Zhao, Jiaxin Fan, Zongbao Feng, Peng Jia
arXiv:2606. 07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification.
By Raphael C Kim, Jingsen Zhu, Ramin Zabih, Michele Santacatterina
arXiv:2607. 21806v1 Announce Type: new Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice.
By Jonathan Zhang, Erik Skalnes, Jacob Chen, Michael Oberst
arXiv:2606. 15333v1 Announce Type: cross Abstract: LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility.
By Zirui Pang, Chenlong Zhang, Haosheng Tan, Zhuoran Jin, Jiaheng Wei, Zixin Zhong
arXiv:2605. 26704v2 Announce Type: replace-cross Abstract: Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread, creating feedback loops that induce distribution shifts at policy intervention points.
By Haochun Wang, Sendong Zhao, Jingbo Wang, Yanrui Du, Ting Liu, Bing Qin