English
Related papers

Related papers: SNPL: Simultaneous Policy Learning and Evaluation …

200 papers

Our goal is to compute a policy that guarantees improved return over a baseline policy even when the available MDP model is inaccurate. The inaccurate model may be constructed, for example, by system identification techniques when the true…

Optimization and Control · Mathematics 2015-06-17 Yinlam Chow , Marek Petrik , Mohammad Ghavamzadeh

Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs suffers from inconsistent boundary-case performance and high inference costs. Training…

Computation and Language · Computer Science 2026-04-29 Arnon Mazza , Elad Levi

In many modern machine learning applications, the outcome is expensive or time-consuming to collect while the predictor information is easy to obtain. Semi-supervised learning (SSL) aims at utilizing large amounts of `unlabeled' data along…

Methodology · Statistics 2017-11-16 Jessica Gronsbell , Tianxi Cai

Policy learning algorithms are widely used in areas such as personalized medicine and advertising to develop individualized treatment regimes. However, most methods force a decision even when predictions are uncertain, which is risky in…

Machine Learning · Computer Science 2026-01-30 Ayush Sawarni , Jikai Jin , Justin Whitehouse , Vasilis Syrgkanis

Achieving both optimality and safety under unknown system dynamics is a central challenge in real-world deployment of agents. To address this, we introduce a notion of maximum safe dynamics learning, where sufficient exploration is…

Systems and Control · Electrical Eng. & Systems 2026-02-24 Manish Prajapat , Johannes Köhler , Melanie N. Zeilinger , Andreas Krause

Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov…

Artificial Intelligence · Computer Science 2025-08-20 Kasper Engelen , Guillermo A. Pérez , Marnix Suilen

This paper presents a supervised multi-agent safe policy learning (SMAS-PL) method for optimal power management of networked microgrids (MGs) in distribution systems. While conventional reinforcement learning (RL) algorithms are black-box…

Systems and Control · Electrical Eng. & Systems 2020-10-28 Qianzhi Zhang , Kaveh Dehghanpour , Zhaoyu Wang , Feng Qiu , Dongbo Zhao

Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks. While several works in the past have proposed methods that are safe for deployment, they assume that the underlying…

Machine Learning · Computer Science 2020-12-21 Yash Chandak , Scott M. Jordan , Georgios Theocharous , Martha White , Philip S. Thomas

Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…

Machine Learning · Computer Science 2022-07-05 Francesco Faccio , Aditya Ramesh , Vincent Herrmann , Jean Harb , Jürgen Schmidhuber

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are…

Computation and Language · Computer Science 2023-11-03 Song Wang , Zhen Tan , Ruocheng Guo , Jundong Li

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely…

Machine Learning · Computer Science 2026-04-21 Dong Yan , Jian Liang , Yanbo Wang , Shuo Lu , Ran He , Tieniu Tan

The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to…

Machine Learning · Computer Science 2021-04-20 Mamshad Nayeem Rizve , Kevin Duarte , Yogesh S Rawat , Mubarak Shah

Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abundance of uninformative samples and tokens. To tackle this…

Machine Learning · Computer Science 2025-09-29 Chao Wang , Tao Yang , Hongtao Tian , Yunsheng Shi , Qiyao Ma , Xiaotao Liu , Ting Yao , Wenbo Ding

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…

Machine Learning · Computer Science 2021-02-26 Miguel Calvo-Fullana , Luiz F. O. Chamon , Santiago Paternain

Ensuring safety and meeting temporal specifications are critical challenges for long-term robotic tasks. Signal temporal logic (STL) has been widely used to systematically and rigorously specify these requirements. However, traditional…

Machine Learning · Computer Science 2023-09-12 Yue Meng , Chuchu Fan

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Machine Learning · Computer Science 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and…

Machine Learning · Computer Science 2023-08-04 Ruixuan Xiao , Yiwen Dong , Haobo Wang , Lei Feng , Runze Wu , Gang Chen , Junbo Zhao

Learning in strategy games (e.g. StarCraft, poker) requires the discovery of diverse policies. This is often achieved by iteratively training new policies against existing ones, growing a policy population that is robust to exploit. This…

Artificial Intelligence · Computer Science 2022-02-16 Siqi Liu , Luke Marris , Daniel Hennes , Josh Merel , Nicolas Heess , Thore Graepel

A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe control provide stability and safety guarantees but are limited…

Robotics · Computer Science 2024-04-30 Wenli Xiao , Tairan He , John Dolan , Guanya Shi