English
Related papers

Related papers: Policy Certificates: Towards Accountable Reinforce…

200 papers

The dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk. We motivate this problem of finding an allocation policy within a…

Artificial Intelligence · Computer Science 2020-12-23 Nymisha Bandi , Theja Tulabandhula

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether…

Machine Learning · Statistics 2024-08-09 Kevin Tan , Wei Fan , Yuting Wei

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Machine Learning · Computer Science 2023-10-11 Wenzhuo Zhou

Most learning algorithms with formal regret guarantees assume that all mistakes are recoverable and essentially rely on trying all possible behaviors. This approach is problematic when some mistakes are "catastrophic", i.e., irreparable. We…

Machine Learning · Computer Science 2025-08-07 Benjamin Plaut , Hanlin Zhu , Stuart Russell

A common technique in reinforcement learning is to evaluate the value function from Monte Carlo simulations of a given policy, and use the estimated value function to obtain a new policy which is greedy with respect to the estimated value…

Machine Learning · Computer Science 2023-03-01 Anna Winnicki , R. Srikant

In some applications of reinforcement learning, a dataset of pre-collected experience is already available but it is also possible to acquire some additional online data to help improve the quality of the policy. However, it may be…

Machine Learning · Computer Science 2023-07-11 Ruiqi Zhang , Andrea Zanette

The famous Policy Iteration algorithm alternates between policy improvement and policy evaluation. Implementations of this algorithm with several variants of the latter evaluation stage, e.g, $n$-step and trace-based returns, have been…

Artificial Intelligence · Computer Science 2018-08-01 Yonathan Efroni , Gal Dalal , Bruno Scherrer , Shie Mannor

Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or…

Machine Learning · Computer Science 2022-03-22 Marius Memmel , Puze Liu , Davide Tateo , Jan Peters

Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving…

Machine Learning · Computer Science 2026-05-27 Tingting Ni , Maryam Kamgarpour

Certified defenses against small-norm adversarial examples have received growing attention in recent years; though certified accuracies of state-of-the-art methods remain far below their non-robust counterparts, despite the fact that…

Machine Learning · Computer Science 2023-01-24 Klas Leino

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

Machine Learning · Computer Science 2024-05-06 Zhongchang Sun , Sihong He , Fei Miao , Shaofeng Zou

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Artificial Intelligence · Computer Science 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

Many dynamic decision problems, such as robotic control, involve a series of tasks, many of which are unknown at training time. Typical approaches for these problems, such as multi-task and meta reinforcement learning, do not generalize…

Machine Learning · Computer Science 2025-05-28 Luise Ge , Michael Lanier , Anindya Sarkar , Bengisu Guresti , Chongjie Zhang , Yevgeniy Vorobeychik

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its instance-dependent…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Aymen Al-Marjani , Emilie Kaufmann

We revisit the Reinforce policy gradient algorithm from the literature. Note that this algorithm typically works with cost returns obtained over random length episodes obtained from either termination upon reaching a goal state (as with…

Machine Learning · Computer Science 2023-10-10 Shalabh Bhatnagar

A learning method is self-certified if it uses all available data to simultaneously learn a predictor and certify its quality with a tight statistical certificate that is valid on unseen data. Recent work has shown that neural network…

Machine Learning · Computer Science 2021-12-13 Maria Perez-Ortiz , Omar Rivasplata , Emilio Parrado-Hernandez , Benjamin Guedj , John Shawe-Taylor

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

Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have grown substantially. To aid RL researchers and production…

Machine Learning · Statistics 2020-02-14 Stephanie C. Y. Chan , Samuel Fishman , John Canny , Anoop Korattikara , Sergio Guadarrama

This paper presents four theoretical contributions that improve the usability of risk certificates for neural networks based on PAC-Bayes bounds. First, two bounds on the KL divergence between Bernoulli distributions enable the derivation…

Machine Learning · Computer Science 2025-11-12 Diego García-Pérez , Emilio Parrado-Hernández , John Shawe-Taylor

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Machine Learning · Computer Science 2018-12-27 Chen Tessler , Daniel J. Mankowitz , Shie Mannor