English
Related papers

Related papers: Delightful Policy Gradient

200 papers

The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do…

Machine Learning · Computer Science 2020-03-02 Chris Nota , Philip S. Thomas

Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning…

Machine Learning · Computer Science 2026-02-24 Wendi Li , Sharon Li

Policy gradient methods are a vital ingredient behind the success of modern reinforcement learning. Modern policy gradient methods, although successful, introduce a residual error in gradient estimation. In this work, we argue that this…

Machine Learning · Computer Science 2024-03-05 Pulkit Katdare , Anant Joshi , Katherine Driggs-Campbell

We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making…

Machine Learning · Computer Science 2023-09-28 Germano Gabbianelli , Gergely Neu , Matteo Papini

Approaches to policy optimization have been motivated from diverse principles, based on how the parametric model is interpreted (e.g. value versus policy representation) or how the learning objective is formulated, yet they share a common…

Machine Learning · Computer Science 2022-06-20 Ramki Gummadi , Saurabh Kumar , Junfeng Wen , Dale Schuurmans

Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional…

Machine Learning · Computer Science 2018-03-21 Cathy Wu , Aravind Rajeswaran , Yan Duan , Vikash Kumar , Alexandre M Bayen , Sham Kakade , Igor Mordatch , Pieter Abbeel

The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy…

Machine Learning · Computer Science 2013-01-18 Tingting Zhao , Hirotaka Hachiya , Voot Tangkaratt , Jun Morimoto , Masashi Sugiyama

Reinforcement learning (RL) shows great potential in sequential decision-making. At present, mainstream RL algorithms are data-driven, which usually yield better asymptotic performance but much slower convergence compared with model-driven…

Machine Learning · Computer Science 2024-02-27 Yang Guan , Jingliang Duan , Shengbo Eben Li , Jie Li , Jianyu Chen , Bo Cheng

Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization of historical trajectories obtained from previous policies is…

Machine Learning · Computer Science 2025-03-06 Yifan Lin , Yuhao Wang , Enlu Zhou

Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL…

Artificial Intelligence · Computer Science 2026-03-25 Xianwei Cao , Dou Quan , Zhenliang Zhang , Shuang Wang

Contextual bandit algorithms often estimate reward models to inform decision-making. However, true rewards can contain action-independent redundancies that are not relevant for decision-making. We show it is more data-efficient to estimate…

Machine Learning · Computer Science 2023-02-27 Aldo Gael Carranza , Sanath Kumar Krishnamurthy , Susan Athey

Distributed learning has gained significant attention due to its advantages in scalability, privacy, and fault tolerance.In this paradigm, multiple agents collaboratively train a global model by exchanging parameters only with their…

Machine Learning · Computer Science 2026-03-31 Ziqin Chen , Yongqiang Wang

This note reconciles two seemingly distinct approaches to policy gradient optimization for the Pass@K objective in reinforcement learning with verifiable rewards: (1) direct REINFORCE-style methods, and (2) advantage-shaping techniques that…

Machine Learning · Computer Science 2026-03-24 Christos Thrampoulidis , Sadegh Mahdavi , Wenlong Deng

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance.…

Machine Learning · Statistics 2017-09-18 Yingfei Wang , Chu Wang , Warren Powell

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…

Machine Learning · Computer Science 2024-10-10 Junlin Wu , Jiongxiao Wang , Chaowei Xiao , Chenguang Wang , Ning Zhang , Yevgeniy Vorobeychik

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when…

Machine Learning · Statistics 2020-05-05 Kamil Ciosek , Shimon Whiteson

Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems. They rely on fresh on-policy data, making them sample-inefficient and requiring…

Machine Learning · Computer Science 2026-02-03 Alessandro Montenegro , Federico Mansutti , Marco Mussi , Matteo Papini , Alberto Maria Metelli

We show that the \emph{stochastic gradient} bandit algorithm converges to a \emph{globally optimal} policy at an $O(1/t)$ rate, even with a \emph{constant} step size. Remarkably, global convergence of the stochastic gradient bandit…

Machine Learning · Computer Science 2024-02-28 Jincheng Mei , Zixin Zhong , Bo Dai , Alekh Agarwal , Csaba Szepesvari , Dale Schuurmans

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency.…

Machine Learning · Computer Science 2018-11-16 Sergey Pankov