English
Related papers

Related papers: Convergent Actor-Critic Algorithms Under Off-Polic…

200 papers

In this paper, we present a probability one convergence proof, under suitable conditions, of a certain class of actor-critic algorithms for finding approximate solutions to entropy-regularized MDPs using the machinery of stochastic…

Machine Learning · Computer Science 2019-10-23 Wesley Suttle , Zhuoran Yang , Kaiqing Zhang , Ji Liu

Reinforcement learning algorithms are highly sensitive to the choice of hyperparameters, typically requiring significant manual effort to identify hyperparameters that perform well on a new domain. In this paper, we take a step towards…

Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional…

Machine Learning · Computer Science 2024-06-21 Michal Nauman , Michał Bortkiewicz , Piotr Miłoś , Tomasz Trzciński , Mateusz Ostaszewski , Marek Cygan

Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably. Ideally, agents should learn and execute…

Machine Learning · Computer Science 2022-10-12 Yuchen Xiao , Weihao Tan , Christopher Amato

Actor Critic methods have found immense applications on a wide range of Reinforcement Learning tasks especially when the state-action space is large. In this paper, we consider actor critic and natural actor critic algorithms with function…

Machine Learning · Computer Science 2025-09-01 Prashansa Panda , Shalabh Bhatnagar

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 study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms…

Machine Learning · Computer Science 2023-12-12 Ruida Zhou , Tao Liu , Min Cheng , Dileep Kalathil , P. R. Kumar , Chao Tian

Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also…

Machine Learning · Computer Science 2020-07-09 Thomas Spooner , Rahul Savani

We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment,…

Machine Learning · Computer Science 2020-03-17 Ryan Lowe , Yi Wu , Aviv Tamar , Jean Harb , Pieter Abbeel , Igor Mordatch

Actor-critic methods integrating target networks have exhibited a stupendous empirical success in deep reinforcement learning. However, a theoretical understanding of the use of target networks in actor-critic methods is largely missing in…

Machine Learning · Computer Science 2022-02-24 Anas Barakat , Pascal Bianchi , Julien Lehmann

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

The average-reward formulation of reinforcement learning (RL) has drawn increased interest in recent years for its ability to solve temporally-extended problems without relying on discounting. Meanwhile, in the discounted setting,…

Machine Learning · Computer Science 2025-08-06 Jacob Adamczyk , Volodymyr Makarenko , Stas Tiomkin , Rahul V. Kulkarni

Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency. An AC based policy optimization process is iterative and needs to…

Machine Learning · Computer Science 2021-12-02 Chayan Banerjee , Zhiyong Chen , Nasimul Noman , Mohsen Zamani

Actor-critic methods, a type of model-free reinforcement learning (RL), have achieved state-of-the-art performances in many real-world domains in continuous control. Despite their success, the wide-scale deployment of these models is still…

Machine Learning · Computer Science 2020-12-14 Srinjoy Roy , Saptam Bakshi , Tamal Maharaj

Policy Dual Averaging (PDA) offers a principled Policy Mirror Descent (PMD) framework that more naturally admits value function approximation than standard PMD, enabling the use of approximate advantage (or Q-) functions while retaining…

Machine Learning · Computer Science 2026-03-12 Ji Gao , Caleb Ju , Guanghui Lan , Zhaohui Tong

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the curse of…

Machine Learning · Computer Science 2021-12-28 Yuwei Luo , Zhuoran Yang , Zhaoran Wang , Mladen Kolar

Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning. Many such methods take the form of actor-critic with…

Machine Learning · Computer Science 2022-05-26 Xueguang Lyu , Andrea Baisero , Yuchen Xiao , Christopher Amato

This work extends an established critic match loss landscape visualization method from online to off-policy reinforcement learning (RL), aiming to reveal the optimization geometry behind critic learning. Off-policy RL differs from stepwise…

Machine Learning · Computer Science 2026-03-17 Jingyi Liu , Jian Guo , Eberhard Gill

We propose a reinforcement learning (RL) framework under a broad class of risk objectives, characterized by convex scoring functions. This class covers many common risk measures, such as variance, Expected Shortfall, entropic Value-at-Risk,…

Mathematical Finance · Quantitative Finance 2025-05-16 Shanyu Han , Yang Liu , Xiang Yu

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that…

Machine Learning · Computer Science 2011-01-04 Michael Fairbank , Eduardo Alonso