English
Related papers

Related papers: An Alternate Policy Gradient Estimator for Softmax…

200 papers

This is a short communication on a Lyapunov function argument for softmax in bandit problems. There are a number of excellent papers coming out using differential equations for policy gradient algorithms in reinforcement learning…

Machine Learning · Computer Science 2020-07-21 Neil Walton

Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics. In spite of its empirical success, a rigorous understanding of the global…

Optimization and Control · Mathematics 2020-06-30 Kaiqing Zhang , Alec Koppel , Hao Zhu , Tamer Başar

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain…

Machine Learning · Computer Science 2021-04-07 Chenjun Xiao , Yifan Wu , Tor Lattimore , Bo Dai , Jincheng Mei , Lihong Li , Csaba Szepesvari , Dale Schuurmans

Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…

Machine Learning · Computer Science 2021-11-24 Thomas Spooner , Nelson Vadori , Sumitra Ganesh

Estimating optimal dynamic policies from offline data is a fundamental problem in dynamic decision making. In the context of causal inference, the problem is known as estimating the optimal dynamic treatment regime. Even though there exists…

Econometrics · Economics 2023-12-15 Qizhao Chen , Morgane Austern , Vasilis Syrgkanis

We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality…

Machine Learning · Statistics 2017-02-14 Kirthevasan Kandasamy , Yoram Bachrach , Ryota Tomioka , Daniel Tarlow , David Carter

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

Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…

Machine Learning · Computer Science 2023-10-11 Siddhant Agarwal , Ishan Durugkar , Peter Stone , Amy Zhang

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies.…

Machine Learning · Statistics 2024-11-01 Otmane Sakhi , Imad Aouali , Pierre Alquier , Nicolas Chopin

Recent work on policy learning from observational data has highlighted the importance of efficient policy evaluation and has proposed reductions to weighted (cost-sensitive) classification. But, efficient policy evaluation need not yield…

Machine Learning · Computer Science 2020-02-13 Andrew Bennett , Nathan Kallus

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic…

Machine Learning · Statistics 2022-09-13 Shicong Cen , Chen Cheng , Yuxin Chen , Yuting Wei , Yuejie Chi

Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscent of techniques from…

In many applications we seek to maximize an expectation with respect to a distribution over discrete variables. Estimating gradients of such objectives with respect to the distribution parameters is a challenging problem. We analyze…

Machine Learning · Statistics 2019-06-18 Evgeny Andriyash , Arash Vahdat , Bill Macready

Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is…

Machine Learning · Computer Science 2018-03-30 Tianbing Xu , Qiang Liu , Jian Peng

This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major…

Systems and Control · Electrical Eng. & Systems 2026-05-14 Junya Ikemoto

Motivated by the poor performance of cross-validation in settings where data are scarce, we propose a novel estimator of the out-of-sample performance of a policy in data-driven optimization.Our approach exploits the optimization problem's…

Optimization and Control · Mathematics 2022-08-04 Vishal Gupta , Michael Huang , Paat Rusmevichientong

We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model…

Machine Learning · Statistics 2017-11-15 Yu-Xiang Wang , Alekh Agarwal , Miroslav Dudik

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