English
Related papers

Related papers: Action-depedent Control Variates for Policy Optimi…

200 papers

Optimal tracking of continuous time nonlinear systems has been extensively studied in literature. However, in several applications, absence of knowledge about system dynamics poses a severe challenge to solving the optimal tracking problem.…

Systems and Control · Electrical Eng. & Systems 2020-01-22 Amardeep Mishra , Satadal Ghosh

We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000).

Artificial Intelligence · Computer Science 2017-06-22 Philip S. Thomas , Emma Brunskill

We present $\varepsilon$-retrain, an exploration strategy encouraging a behavioral preference while optimizing policies with monotonic improvement guarantees. To this end, we introduce an iterative procedure for collecting retrain areas --…

Artificial Intelligence · Computer Science 2025-04-15 Luca Marzari , Priya L. Donti , Changliu Liu , Enrico Marchesini

For reinforcement learning on complex stochastic systems where many factors dynamically impact the output trajectories, it is desirable to effectively leverage the information from historical samples collected in previous iterations to…

Machine Learning · Statistics 2022-09-13 Hua Zheng , Wei Xie , M. Ben Feng

The ability to learn and execute optimal control policies safely is critical to realization of complex autonomy, especially where task restarts are not available and/or the systems are safety-critical. Safety requirements are often…

Systems and Control · Electrical Eng. & Systems 2021-10-06 S M Nahid Mahmud , Moad Abudia , Scott A Nivison , Zachary I. Bell , Rushikesh Kamalapurkar

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Machine Learning · Computer Science 2021-04-21 Tianyi Chen , Kaiqing Zhang , Georgios B. Giannakis , Tamer Başar

We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution…

Machine Learning · Computer Science 2019-11-26 Chen Tessler , Guy Tennenholtz , Shie Mannor

Continuous control is a widely applicable area of reinforcement learning. The main players of this area are actor-critic methods that utilize policy gradients of neural approximators as a common practice. The focus of our study is to show…

Machine Learning · Computer Science 2020-09-08 Recep Yusuf Bekci , Mehmet Gümüş

While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations. Recent works have demonstrated…

Machine Learning · Computer Science 2023-05-23 Kang Xu , Yan Ma , Bingsheng Wei , Wei Li

Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only…

Machine Learning · Statistics 2018-02-23 Voot Tangkaratt , Abbas Abdolmaleki , Masashi Sugiyama

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general…

Optimization and Control · Mathematics 2024-03-04 Deyue Li

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

Machine Learning · Computer Science 2023-01-31 Harshat Kumar , Alec Koppel , Alejandro Ribeiro

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2021-07-06 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

We study policy gradient for mean-field control in continuous time in a reinforcement learning setting. By considering randomised policies with entropy regularisation, we derive a gradient expectation representation of the value function,…

Machine Learning · Statistics 2023-03-14 Noufel Frikha , Maximilien Germain , Mathieu Laurière , Huyên Pham , Xuanye Song

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›