English
Related papers

Related papers: Lipschitzness Is All You Need To Tame Off-policy G…

200 papers

A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are no guarantees on…

Machine Learning · Statistics 2023-12-27 Paul Daoudi , Mathias Formoso , Othman Gaizi , Achraf Azize , Evrard Garcelon

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In…

Machine Learning · Computer Science 2025-12-01 Charles Arnal , Gaëtan Narozniak , Vivien Cabannes , Yunhao Tang , Julia Kempe , Remi Munos

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

Lipschitz bandit is a variant of stochastic bandits that deals with a continuous arm set defined on a metric space, where the reward function is subject to a Lipschitz constraint. In this paper, we introduce a new problem of Lipschitz…

Machine Learning · Computer Science 2023-10-10 Yue Kang , Cho-Jui Hsieh , Thomas C. M. Lee

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that…

Machine Learning · Computer Science 2011-01-04 Michael Fairbank , Eduardo Alonso

Lipschitz continuity is a crucial functional property of any predictive model, that naturally governs its robustness, generalisation, as well as adversarial vulnerability. Contrary to other works that focus on obtaining tighter bounds and…

Machine Learning · Computer Science 2024-05-16 Grigory Khromov , Sidak Pal Singh

Behavior Cloning (BC) is an effective imitation learning technique and has even been adopted in some safety-critical domains such as autonomous vehicles. BC trains a policy to mimic the behavior of an expert by using a dataset composed of…

Machine Learning · Computer Science 2025-08-12 Shili Wu , Yizhao Jin , Puhua Niu , Aniruddha Datta , Sean B. Andersson

Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental…

Artificial Intelligence · Computer Science 2016-06-01 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

Lipschitz bandits is a prominent version of multi-armed bandits that studies large, structured action spaces such as the $[0,1]$ interval, where similar actions are guaranteed to have similar rewards. A central theme here is the adaptive…

Machine Learning · Computer Science 2025-06-13 Chara Podimata , Aleksandrs Slivkins

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative…

Machine Learning · Computer Science 2024-05-24 Qian Shao , Pradeep Varakantham , Shih-Fen Cheng

Imitation Learning from observation describes policy learning in a similar way to human learning. An agent's policy is trained by observing an expert performing a task. While many state-only imitation learning approaches are based on…

Machine Learning · Computer Science 2024-10-02 Damian Boborzi , Christoph-Nikolas Straehle , Jens S. Buchner , Lars Mikelsons

One of the key issues for imitation learning lies in making policy learned from limited samples to generalize well in the whole state-action space. This problem is much more severe in high-dimensional state environments, such as game…

Machine Learning · Computer Science 2021-07-02 Xin-Qiang Cai , Yao-Xiang Ding , Yuan Jiang , Zhi-Hua Zhou

Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a…

Machine Learning · Computer Science 2012-03-05 Alekh Agarwal , Miroslav Dudík , Satyen Kale , John Langford , Robert E. Schapire

In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all of sequential decision-making theory assumes that all errors are recoverable (e.g., by bounding rewards). Standard bandit algorithms that…

Machine Learning · Computer Science 2026-04-14 Sarah Liaw , Benjamin Plaut

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical…

Computation and Language · Computer Science 2025-07-01 Yi-Chen Li , Tian Xu , Yang Yu , Xuqin Zhang , Xiong-Hui Chen , Zhongxiang Ling , Ningjing Chao , Lei Yuan , Zhi-Hua Zhou

In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs. We study the property of the optimal discriminative function and show that in many GANs, the gradient from the optimal…

Machine Learning · Computer Science 2018-12-27 Zhiming Zhou , Yuxuan Song , Lantao Yu , Hongwei Wang , Jiadong Liang , Weinan Zhang , Zhihua Zhang , Yong Yu

We study the problem of learning to generate an answer (or completion) to a question (or prompt), where there could be multiple correct answers, any one of which is acceptable at test time. Learning is based on demonstrations of some…

Machine Learning · Computer Science 2026-02-27 Nirmit Joshi , Gene Li , Siddharth Bhandari , Shiva Prasad Kasiviswanathan , Cong Ma , Nathan Srebro

This paper demonstrates the robustness of Lipschitz-regularized $\alpha$-divergences as objective functionals in generative modeling, showing they enable stable learning across a wide range of target distributions with minimal assumptions.…

Machine Learning · Statistics 2025-09-09 Ziyu Chen , Hyemin Gu , Markos A. Katsoulakis , Luc Rey-Bellet , Wei Zhu

A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable…

Machine Learning · Computer Science 2019-02-21 Paulo Rauber , Avinash Ummadisingu , Filipe Mutz , Juergen Schmidhuber

Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, we firstly analyze…

Machine Learning · Computer Science 2020-10-23 Tian Xu , Ziniu Li , Yang Yu