English
Related papers

Related papers: A Closer Look at Deep Policy Gradients

200 papers

We consider the joint design and control of discrete-time stochastic dynamical systems over a finite time horizon. We formulate the problem as a multi-step optimization problem under uncertainty seeking to identify a system design and a…

Machine Learning · Computer Science 2022-01-07 Adrien Bolland , Ioannis Boukas , Mathias Berger , Damien Ernst

We develop a normative framework for hierarchical model-based policy optimization based on applying second-order methods in the space of all possible state-action paths. The resulting natural path gradient performs policy updates in a…

Machine Learning · Computer Science 2020-01-03 Daniel McNamee

Policy gradient algorithms have found wide adoption in NLP, but have recently become subject to criticism, doubting their suitability for NMT. Choshen et al. (2020) identify multiple weaknesses and suspect that their success is determined…

Computation and Language · Computer Science 2021-06-17 Samuel Kiegeland , Julia Kreutzer

There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and…

Machine Learning · Computer Science 2013-01-14 Lex Weaver , Nigel Tao

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Machine Learning · Computer Science 2020-01-01 Aviral Kumar , Xue Bin Peng , Sergey Levine

Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and…

Neural and Evolutionary Computing · Computer Science 2021-02-09 Jianyong Sun , Xin Liu , Thomas Bäck , Zongben Xu

Consider the problem of training robustly capable agents. One approach is to generate a diverse collection of agent polices. Training can then be viewed as a quality diversity (QD) optimization problem, where we search for a collection of…

Machine Learning · Computer Science 2022-04-18 Bryon Tjanaka , Matthew C. Fontaine , Julian Togelius , Stefanos Nikolaidis

Many reinforcement learning algorithms use value functions to guide the search for better policies. These methods estimate the value of a single policy while generalizing across many states. The core idea of this paper is to flip this…

Machine Learning · Computer Science 2020-02-28 Jean Harb , Tom Schaul , Doina Precup , Pierre-Luc Bacon

Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is…

Machine Learning · Computer Science 2025-02-17 Xueru Wen , Jie Lou , Yaojie Lu , Hongyu Lin , Xing Yu , Xinyu Lu , Ben He , Xianpei Han , Debing Zhang , Le Sun

The classical policy gradient method is the theoretical and conceptual foundation of modern policy-based reinforcement learning (RL) algorithms. Most rigorous analyses of such methods, particularly those establishing convergence guarantees,…

Machine Learning · Computer Science 2026-02-11 Jongmin Lee , Ernest K. Ryu

Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In this family of methods, agents are trained to maximize…

Machine Learning · Computer Science 2022-03-24 Ted Moskovitz , Michael Arbel , Jack Parker-Holder , Aldo Pacchiano

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…

Recent advances in deep learning have spurred the development of end-to-end frameworks for portfolio optimization that utilize implicit layers. However, many such implementations are highly sensitive to neural network initialization,…

Portfolio Management · Quantitative Finance 2025-04-29 Manuel Parra-Diaz , Carlos Castro-Iragorri

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization). The PPG objective is a partial variation of the VPG objective and the…

Machine Learning · Computer Science 2020-10-21 Ju-Seung Byun , Byungmoon Kim , Huamin Wang

We develop a method for policy architecture search and adaptation via gradient-free optimization which can learn to perform autonomous driving tasks. By learning from both demonstration and environmental reward we develop a model that can…

Machine Learning · Computer Science 2017-10-18 Sayna Ebrahimi , Anna Rohrbach , Trevor Darrell

Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face…

Machine Learning · Computer Science 2021-07-21 João Carvalho , Davide Tateo , Fabio Muratore , Jan Peters

As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision…

Machine Learning · Computer Science 2020-06-19 Annie Xie , James Harrison , Chelsea Finn

Recently, foundation models such as OpenAI's O1 and O3, along with DeepSeek's R1, have demonstrated strong reasoning capacities and problem-solving skills acquired through large-scale reinforcement learning (RL), with wide applications in…

Machine Learning · Computer Science 2025-04-29 Tianbing Xu

We investigate and analyze principles of typical motion planning algorithms. These include traditional planning algorithms, supervised learning, optimal value reinforcement learning, policy gradient reinforcement learning. Traditional…

Robotics · Computer Science 2021-02-08 Chengmin Zhou , Bingding Huang , Pasi Fränti

We introduce a learning method called ``gradient-based reinforcement planning'' (GREP). Unlike traditional DP methods that improve their policy backwards in time, GREP is a gradient-based method that plans ahead and improves its policy…

Artificial Intelligence · Computer Science 2007-05-23 Ivo Kwee , Marcus Hutter , Juergen Schmidhuber