English
Related papers

Related papers: Provably Convergent Policy Optimization via Metric…

200 papers

Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However,…

Artificial Intelligence · Computer Science 2024-11-01 Matthew V Macfarlane , Edan Toledo , Donal Byrne , Paul Duckworth , Alexandre Laterre

We establish a connection between distributionally robust optimization (DRO) and classical robust statistics. We demonstrate that this connection arises naturally in the context of estimation under data corruption, where the goal is to…

Optimization and Control · Mathematics 2024-10-21 Gabriel Chan , Bart Van Parys , Amine Bennouna

Policy gradient reinforcement learning techniques enable an agent to directly learn an optimal action policy through the interactions with the environment. Nevertheless, despite its advantages, it sometimes suffers from slow convergence…

Information Theory · Computer Science 2020-08-05 Mohammad G. Khoshkholgh , Halim Yanikomeroglu

In the post-training of large language models (LLMs), Reinforcement Learning from Human Feedback (RLHF) is an effective approach to achieve generation aligned with human preferences. Direct Preference Optimization (DPO) allows for policy…

Machine Learning · Computer Science 2025-06-16 Motoki Omura , Yasuhiro Fujita , Toshiki Kataoka

Despite superior performance in many situations, deep neural networks are often vulnerable to adversarial examples and distribution shifts, limiting model generalization ability in real-world applications. To alleviate these problems,…

Machine Learning · Computer Science 2023-02-14 Hoang Phan , Trung Le , Trung Phung , Tuan Anh Bui , Nhat Ho , Dinh Phung

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Computation and Language · Computer Science 2024-09-27 Jian Li , Haojing Huang , Yujia Zhang , Pengfei Xu , Xi Chen , Rui Song , Lida Shi , Jingwen Wang , Hao Xu

We study reinforcement learning (RL) in the setting of continuous time and space, for an infinite horizon with a discounted objective and the underlying dynamics driven by a stochastic differential equation. Built upon recent advances in…

Machine Learning · Computer Science 2023-10-19 Hanyang Zhao , Wenpin Tang , David D. Yao

Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to…

Machine Learning · Computer Science 2019-05-28 Supratik Paul , Michael A. Osborne , Shimon Whiteson

Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large language models. Yet existing methods share a common blind spot: they optimize policies…

Machine Learning · Computer Science 2026-04-29 Huaiyang Wang , Xiaojie Li , Deqing Wang , Haoyi Zhou , Zixuan Huang , Yaodong Yang , Jianxin Li , Yikun Ban

Large language models (LLMs) trained with reinforcement objectives often achieve superficially correct answers via shortcut strategies, pairing correct outputs with spurious or unfaithful reasoning and degrading under small causal…

Machine Learning · Computer Science 2025-09-30 Xiangqi Wang , Yue Huang , Yujun Zhou , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Policy gradient methods usually rely on entropy regularization to prevent premature convergence. However, maximizing entropy indiscriminately pushes the policy towards a uniform distribution, often overriding the reward signal if not…

Machine Learning · Computer Science 2026-03-06 Luca Serfilippi , Giorgio Franceschelli , Antonio Corradi , Mirco Musolesi

Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model-Based Policy Optimization (RMB-PO). A variant of RMB-PO,…

Machine Learning · Computer Science 2024-02-27 Ziniu Li , Tian Xu , Yang Yu

This paper proposes a distributionally robust unit commitment approach for microgrids under net load and electricity market price uncertainty. The key thrust of the proposed approach is to leverage the Kullback-Leibler divergence to…

Optimization and Control · Mathematics 2020-12-15 Ogun Yurdakul , Fikret Sivrikaya , Sahin Albayrak

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

We propose a nonsmooth trust-region method for solving optimization problems with locally Lipschitz continuous functions, with application to problems constrained by variational inequalities of the second kind. Under suitable assumptions on…

Optimization and Control · Mathematics 2018-01-17 Constantin Christof , Juan Carlos De Los Reyes , Christian Meyer

Adversarially robust optimization (ARO) has emerged as the *de facto* standard for training models that hedge against adversarial attacks in the test stage. While these models are robust against adversarial attacks, they tend to suffer…

Optimization and Control · Mathematics 2025-06-12 Aras Selvi , Eleonora Kreacic , Mohsen Ghassemi , Vamsi Potluru , Tucker Balch , Manuela Veloso

We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent. In order to see this, one should simply plug Kullback-Leibler divergence in both mirror map and…

Machine Learning · Computer Science 2019-09-17 Konstantin Mishchenko

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

Machine Learning · Computer Science 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez

Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable solutions by hedging against data perturbations in Wasserstein distance. Despite its recent empirical success in operations research and machine…

Machine Learning · Computer Science 2022-05-03 Rui Gao

Adaptive trust-region methods attempt to maintain strong convergence guarantees without depending on conservative estimates of problem properties such as Lipschitz constants. However, on close inspection, one can show existing adaptive…

Optimization and Control · Mathematics 2024-08-06 Fadi Hamad , Oliver Hinder
‹ Prev 1 8 9 10 Next ›