English
Related papers

Related papers: PAC Guarantees for Reinforcement Learning: Sample …

200 papers

As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamental challenges: outcome-only rewards fail to precisely attribute credit to intermediate steps,…

Computation and Language · Computer Science 2026-04-30 Mukai Li , Qingcheng Zeng , Tianqing Fang , Zhenwen Liang , Linfeng Song , Qi Liu , Haitao Mi , Dong Yu

The ultimate performance of machine learning algorithms for classification tasks is usually measured in terms of the empirical error probability (or accuracy) based on a testing dataset. Whereas, these algorithms are optimized through the…

Machine Learning · Computer Science 2021-12-13 Matias Vera , Leonardo Rey Vega , Pablo Piantanida

Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy.…

Machine Learning · Computer Science 2026-04-27 Liangzu Peng , Uday Kiran Reddy Tadipatri , Ziqing Xu , Eric Eaton , René Vidal

This dissertation investigates how reinforcement learning (RL) methods can be designed to be safe, sample-efficient, and robust. Framed through the unifying perspective of contextual-bandit RL, the work addresses two major application…

Machine Learning · Computer Science 2025-10-20 Shashank Gupta

The traditional notion of generalization---i.e., learning a hypothesis whose empirical error is close to its true error---is surprisingly brittle. As has recently been noted in [DFH+15b], even if several algorithms have this guarantee in…

Data Structures and Algorithms · Computer Science 2016-06-03 Rachel Cummings , Katrina Ligett , Kobbi Nissim , Aaron Roth , Zhiwei Steven Wu

We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function…

Machine Learning · Computer Science 2022-06-16 Jinglin Chen , Nan Jiang

The Structure Gap between probabilistic LLM generation and deterministic schema requirements hinders automated workflows. We propose RL-Struct, a lightweight framework using Gradient Regularized Policy Optimization (GRPO) with a…

Artificial Intelligence · Computer Science 2025-12-16 Ruike Hu , Shulei Wu

Probably Approximately Correct (PAC) bounds are widely used to derive probabilistic guarantees for the generalisation of machine learning models. They highlight the components of the model which contribute to its generalisation capacity.…

Machine Learning · Computer Science 2024-07-30 Thomas Walker , Alessio Lomuscio

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

A supervised learning framework is proposed to approximate a model predictive controller (MPC) with reduced computational complexity and guarantees on stability and constraint satisfaction. The framework can be used for a wide class of…

Systems and Control · Computer Science 2018-06-13 Michael Hertneck , Johannes Köhler , Sebastian Trimpe , Frank Allgöwer

Modern Reinforcement Learning (RL) is more than just learning the optimal policy; Alternative learning goals such as exploring the environment, estimating the underlying model, and learning from preference feedback are all of practical…

Machine Learning · Computer Science 2024-12-24 Fan Chen , Song Mei , Yu Bai

For a constraint satisfaction problem (CSP), a robust satisfaction algorithm is one that outputs an assignment satisfying most of the constraints on instances that are near-satisfiable. It is known that the CSPs that admit efficient robust…

Data Structures and Algorithms · Computer Science 2025-09-09 Joshua Brakensiek , Venkatesan Guruswami , Sai Sandeep

In offline reinforcement learning (RL) we have no opportunity to explore so we must make assumptions that the data is sufficient to guide picking a good policy, taking the form of assuming some coverage, realizability, Bellman completeness,…

Machine Learning · Computer Science 2023-11-14 Masatoshi Uehara , Nathan Kallus , Jason D. Lee , Wen Sun

Many physical systems have underlying safety considerations that require that the policy employed ensures the satisfaction of a set of constraints. The analytical formulation usually takes the form of a Constrained Markov Decision Process…

Machine Learning · Computer Science 2021-03-03 Aria HasanzadeZonuzy , Archana Bura , Dileep Kalathil , Srinivas Shakkottai

$ \newcommand{\eps}{\varepsilon} $In learning theory, the VC dimension of a concept class $C$ is the most common way to measure its "richness." In the PAC model $$ \Theta\Big(\frac{d}{\eps} + \frac{\log(1/\delta)}{\eps}\Big) $$ examples are…

Quantum Physics · Physics 2017-06-08 Srinivasan Arunachalam , Ronald de Wolf

We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in obtaining…

Machine Learning · Computer Science 2026-02-10 Abdelkrim Zitouni , Mehdi Hennequin , Juba Agoun , Ryan Horache , Nadia Kabachi , Omar Rivasplata

Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent…

Machine Learning · Computer Science 2024-05-09 Akifumi Wachi , Xun Shen , Yanan Sui

Consistent image generation requires faithfully preserving identities, styles, and logical coherence across multiple images, which is essential for applications such as storytelling and character design. Supervised training approaches…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Bowen Ping , Chengyou Jia , Minnan Luo , Changliang Xia , Xin Shen , Zhuohang Dang , Hangwei Qian

This work studies reinforcement learning (RL) in the context of multi-period supply chains subject to constraints, e.g., on production and inventory. We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for…

Machine Learning · Computer Science 2023-02-06 Jaime Sabal Bermúdez , Antonio del Rio Chanona , Calvin Tsay

We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic…

Machine Learning · Computer Science 2019-05-31 Wen Sun , Nan Jiang , Akshay Krishnamurthy , Alekh Agarwal , John Langford