English
Related papers

Related papers: Stabilizing the Q-Gradient Field for Policy Smooth…

200 papers

Value-based algorithms are a cornerstone of off-policy reinforcement learning due to their simplicity and training stability. However, their use has traditionally been restricted to discrete action spaces, as they rely on estimating…

Machine Learning · Computer Science 2025-10-23 Yigit Korkmaz , Urvi Bhuwania , Ayush Jain , Erdem Bıyık

Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability…

Artificial Intelligence · Computer Science 2019-02-08 Hélène Plisnier , Denis Steckelmacher , Diederik M. Roijers , Ann Nowé

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…

Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this approach comes at the expense of training instability, caused…

Machine Learning · Computer Science 2024-06-11 Bahareh Tasdighi , Abdullah Akgül , Manuel Haussmann , Kenny Kazimirzak Brink , Melih Kandemir

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

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

In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong…

Machine Learning · Computer Science 2026-05-26 Safwan Labbi , Paul Mangold , Daniil Tiapkin , Eric Moulines

In this paper, we introduce a policy-gradient method for model-based reinforcement learning (RL) that exploits a type of stationary distributions commonly obtained from Markov decision processes (MDPs) in stochastic networks, queueing…

Machine Learning · Computer Science 2025-10-30 Céline Comte , Matthieu Jonckheere , Jaron Sanders , Albert Senen-Cerda

A critical problem with the practical utility of controllers trained with deep Reinforcement Learning (RL) is the notable lack of smoothness in the actions learned by the RL policies. This trend often presents itself in the form of control…

Robotics · Computer Science 2021-05-28 Siddharth Mysore , Bassel Mabsout , Renato Mancuso , Kate Saenko

Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm…

Machine Learning · Computer Science 2019-06-10 Patrick Nadeem Ward , Ariella Smofsky , Avishek Joey Bose

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly…

Machine Learning · Computer Science 2018-10-25 Esther Derman , Daniel J. Mankowitz , Timothy A. Mann , Shie Mannor

While on-policy algorithms are known for their stability, they often demand a substantial number of samples. In contrast, off-policy algorithms, which leverage past experiences, are considered sample-efficient but tend to exhibit…

Machine Learning · Computer Science 2023-09-28 Jianfei Ma

We study policy gradient (PG) for reinforcement learning in continuous time and space under the regularized exploratory formulation developed by Wang et al. (2020). We represent the gradient of the value function with respect to a given…

Machine Learning · Computer Science 2022-07-26 Yanwei Jia , Xun Yu Zhou

Reinforcement learning (RL) has achieved strong performance in robotic control; however, state-of-the-art policy learning methods, such as actor-critic methods, still suffer from high sample complexity and often produce physically…

Robotics · Computer Science 2026-03-24 Namai Chandra , Liu Mohan , Zhihao Gu , Lin Wang

Actor-critic methods can achieve incredible performance on difficult reinforcement learning problems, but they are also prone to instability. This is partly due to the interaction between the actor and critic during learning, e.g., an…

Machine Learning · Computer Science 2019-02-26 Simone Parisi , Voot Tangkaratt , Jan Peters , Mohammad Emtiyaz Khan

We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that…

Artificial Intelligence · Computer Science 2017-11-27 Ofir Nachum , Mohammad Norouzi , Kelvin Xu , Dale Schuurmans

Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain…

Dynamical Systems · Mathematics 2022-06-14 Pavel Osinenko , Grigory Yaremenko , Ilya Osokin

Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…

Machine Learning · Computer Science 2021-09-27 Chayan Banerjee , Zhiyong Chen , Nasimul Noman

As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to…

Quantum Physics · Physics 2019-07-18 Pantita Palittapongarnpim , Barry C. Sanders

We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…

Machine Learning · Computer Science 2025-12-11 Yang Xu , Swetha Ganesh , Vaneet Aggarwal