English
Related papers

Related papers: Safe Policy Improvement Approaches and their Limit…

200 papers

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also, facilitates a better understanding of an agent's decisions. We tackle this problem in the options…

Artificial Intelligence · Computer Science 2021-07-01 Arushi Jain , Khimya Khetarpal , Doina Precup

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

Machine Learning · Computer Science 2025-12-02 Chang Gao , Chujie Zheng , Xiong-Hui Chen , Kai Dang , Shixuan Liu , Bowen Yu , An Yang , Shuai Bai , Jingren Zhou , Junyang Lin

Ensuring safety is important for the practical deployment of reinforcement learning (RL). Various challenges must be addressed, such as handling stochasticity in the environments, providing rigorous guarantees of persistent state-wise…

Machine Learning · Computer Science 2023-09-26 Milan Ganai , Zheng Gong , Chenning Yu , Sylvia Herbert , Sicun Gao

Learned action policies are increasingly popular in sequential decision-making, but suffer from a lack of safety guarantees. Recent work introduced a pipeline for testing the safety of such policies under initial-state and action-outcome…

Artificial Intelligence · Computer Science 2026-03-17 Johannes Schmalz , Chaahat Jain

Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly…

Machine Learning · Computer Science 2025-12-24 Mahesh Keswani , Raunak Bhattacharyya

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from…

Machine Learning · Computer Science 2020-01-15 Yuhui Wang , Hao He , Chao Wen , Xiaoyang Tan

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the…

Machine Learning · Computer Science 2018-12-27 Quan Vuong , Yiming Zhang , Keith W. Ross

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world…

Machine Learning · Statistics 2017-11-15 Felix Berkenkamp , Matteo Turchetta , Angela P. Schoellig , Andreas Krause

This paper presents a safe robust policy iteration (SR-PI) algorithm to design controllers with satisficing (good enough) performance and safety guarantee. This is in contrast to standard PI-based control design methods with no safety…

Systems and Control · Electrical Eng. & Systems 2020-09-16 Yuzhen Han , Hamidreza Modares

Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However,…

Artificial Intelligence · Computer Science 2023-03-07 Wen-Chi Yang , Giuseppe Marra , Gavin Rens , Luc De Raedt

An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and…

Machine Learning · Statistics 2016-07-14 Marek Petrik , Yinlam Chow , Mohammad Ghavamzadeh

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately,…

Machine Learning · Computer Science 2021-03-01 Elita A. Lobo , Mohammad Ghavamzadeh , Marek Petrik

Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In this paper, we…

Machine Learning · Computer Science 2025-05-06 Hanping Zhang , Yuhong Guo

Multi-task reinforcement learning aims to quickly identify solutions for new tasks with minimal or no additional interaction with the environment. Generalized Policy Improvement (GPI) addresses this by combining a set of base policies to…

Machine Learning · Computer Science 2025-11-14 Lucas N. Alegre , Ana L. C. Bazzan , André Barreto , Bruno C. da Silva

Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…

Machine Learning · Computer Science 2025-02-28 Kaustubh Mani , Vincent Mai , Charlie Gauthier , Annie Chen , Samer Nashed , Liam Paull

Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we…

Machine Learning · Computer Science 2026-05-19 Yifei Chen , Shaoqin Zhu , Xiaoqiang Ji

Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a…

Robotics · Computer Science 2022-11-11 Hai Nguyen , Andrea Baisero , Dian Wang , Christopher Amato , Robert Platt

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Safety is a crucial necessity in many applications of reinforcement learning (RL), whether robotic, automotive, or medical. Many existing approaches to safe RL rely on receiving numeric safety feedback, but in many cases this feedback can…

Machine Learning · Computer Science 2022-10-27 Andrew Bennett , Dipendra Misra , Nathan Kallus

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or…

Machine Learning · Computer Science 2025-03-21 Claire Chen , Shuze Daniel Liu , Shangtong Zhang