English
Related papers

Related papers: Compatible features for Monotonic Policy Improveme…

200 papers

We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value…

Econometrics · Economics 2019-07-23 Mert Demirer , Vasilis Syrgkanis , Greg Lewis , Victor Chernozhukov

We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this…

Machine Learning · Computer Science 2018-06-13 Krzysztof Choromanski , Mark Rowland , Vikas Sindhwani , Richard E. Turner , Adrian Weller

Policy gradient algorithms have been widely applied to Markov decision processes and reinforcement learning problems in recent years. Regularization with various entropy functions is often used to encourage exploration and improve…

Machine Learning · Computer Science 2023-06-09 Haoya Li , Samarth Gupta , Hsiangfu Yu , Lexing Ying , Inderjit Dhillon

In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set…

Machine Learning · Computer Science 2022-06-24 Lucas N. Alegre , Ana L. C. Bazzan , Bruno C. da Silva

Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…

Machine Learning · Computer Science 2020-10-19 Santiago Paternain , Juan Andres Bazerque , Alejandro Ribeiro

Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe their success to the use of parameterized policies. However, while theoretical guarantees have been established for this class of algorithms, especially…

Machine Learning · Statistics 2024-02-14 Carlo Alfano , Rui Yuan , Patrick Rebeschini

We tackle the issue of finding a good policy when the number of policy updates is limited. This is done by approximating the expected policy reward as a sequence of concave lower bounds which can be efficiently maximized, drastically…

Artificial Intelligence · Computer Science 2016-12-30 Nicolas Le Roux

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

We study finite-horizon continuous-time policy evaluation from discrete closed-loop trajectories under time-inhomogeneous dynamics. The target value surface solves a backward parabolic equation, but the Bellman baseline obtained from…

Machine Learning · Statistics 2026-05-11 Yaowei Zheng , Richong Zhang , Shenxi Wu , Shirui Bian , Haosong Zhang , Li Zeng , Xingjian Ma , Yichi Zhang

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

Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine system in neurobiology, recent research has sought to introduce multiple discount factors into…

Machine Learning · Computer Science 2026-05-25 Jing Sun

We present a midpoint policy iteration algorithm to solve linear quadratic optimal control problems in both model-based and model-free settings. The algorithm is a variation of Newton's method, and we show that in the model-based setting it…

Optimization and Control · Mathematics 2022-02-16 Benjamin Gravell , Iman Shames , Tyler Summers

In this paper, we point out a fundamental property of the objective in reinforcement learning, with which we can reformulate the policy gradient objective into a perceptron-like loss function, removing the need to distinguish between on and…

Machine Learning · Computer Science 2019-04-25 Kai-Chun Hu , Chen-Huan Pi , Ting Han Wei , I-Chen Wu , Stone Cheng , Yi-Wei Dai , Wei-Yuan Ye

Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence…

Machine Learning · Computer Science 2019-06-21 Ehsan Imani , Eric Graves , Martha White

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

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

Machine Learning · Computer Science 2024-06-04 Guillermo Infante , David Kuric , Anders Jonsson , Vicenç Gómez , Herke van Hoof

Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sublinear convergence of PPG for sufficiently small step sizes…

Optimization and Control · Mathematics 2024-09-19 Jiacai Liu , Wenye Li , Dachao Lin , Ke Wei , Zhihua Zhang

While Group Relative Policy Optimization (GRPO) has emerged as a scalable framework for critic-free policy learning, extending it to settings with explicit behavioral constraints remains underexplored. We introduce Constrained GRPO, a…

Machine Learning · Computer Science 2026-02-09 Roger Girgis , Rodrigue de Schaetzen , Luke Rowe , Azalée Robitaille , Christopher Pal , Liam Paull

We propose a novel and efficient algorithm for the collaborative preference completion problem, which involves jointly estimating individualized rankings for a set of entities over a shared set of items, based on a limited number of…

Machine Learning · Statistics 2016-11-16 Suriya Gunasekar , Oluwasanmi Koyejo , Joydeep Ghosh

Stochastic resetting, where a dynamical process is intermittently returned to a fixed reference state, has emerged as a powerful mechanism for optimizing first-passage properties. Existing theory largely treats static, non-learning…

Machine Learning · Computer Science 2026-03-18 Jello Zhou , Vudtiwat Ngampruetikorn , David J. Schwab