English
Related papers

Related papers: Actor-Critics Can Achieve Optimal Sample Efficienc…

200 papers

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

The actor-critic RL is widely used in various robotic control tasks. By viewing the actor-critic RL from the perspective of variational inference (VI), the policy network is trained to obtain the approximate posterior of actions given the…

Machine Learning · Computer Science 2022-01-04 Duo Xu , Faramarz Fekri

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…

Machine Learning · Computer Science 2022-11-23 Jiachen Li , Shuo Cheng , Zhenyu Liao , Huayan Wang , William Yang Wang , Qinxun Bai

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL…

Machine Learning · Computer Science 2021-09-28 Zhaorun Chen , Binhao Chen , Shenghan Xie , Liang Gong , Chengliang Liu , Zhengfeng Zhang , Junping Zhang

Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms…

Machine Learning · Computer Science 2022-02-14 Tengyang Xie , Nan Jiang , Huan Wang , Caiming Xiong , Yu Bai

Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training on a physical system can be expensive and dangerous, which…

Robotics · Computer Science 2017-10-19 Lerrel Pinto , Marcin Andrychowicz , Peter Welinder , Wojciech Zaremba , Pieter Abbeel

The goal of offline reinforcement learning (RL) is to find an optimal policy given prerecorded trajectories. Many current approaches customize existing off-policy RL algorithms, especially actor-critic algorithms in which policy evaluation…

Machine Learning · Computer Science 2021-10-07 Wonjoon Goo , Scott Niekum

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup

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

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

Warm-Start reinforcement learning (RL), aided by a prior policy obtained from offline training, is emerging as a promising RL approach for practical applications. Recent empirical studies have demonstrated that the performance of Warm-Start…

Machine Learning · Computer Science 2023-06-21 Hang Wang , Sen Lin , Junshan Zhang

Many popular practical reinforcement learning (RL) algorithms employ evolving reward functions-through techniques such as reward shaping, entropy regularization, or curriculum learning-yet their theoretical foundations remain…

Machine Learning · Computer Science 2025-10-15 Rui Hu , Yu Chen , Longbo Huang

Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert demonstrations bypasses…

Machine Learning · Computer Science 2026-05-19 Sayambhu Sen , Shalabh Bhatnagar

Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample…

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…

Machine Learning · Computer Science 2019-03-25 Yan Zhang , Michael M. Zavlanos

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…

Machine Learning · Computer Science 2026-05-05 Ruiquan Huang , Donghao Li , Yingbin Liang , Jing Yang

In this paper, we establish last-iterate convergence rates for off-policy actor--critic methods in reinforcement learning. In particular, under a single-loop, single-timescale implementation and a broad class of policy updates, including…

Machine Learning · Computer Science 2026-05-14 Ishaq Hamza , Zaiwei Chen

Designing off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy distribution. Prior off-policy actor-critic (AC) algorithms…

Machine Learning · Computer Science 2021-07-20 Tengyu Xu , Zhuoran Yang , Zhaoran Wang , Yingbin Liang

Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is desired to ensure the reliability of an algorithm. In this…

Machine Learning · Computer Science 2021-02-04 Arushi Jain , Gandharv Patil , Ayush Jain , Khimya Khetarpal , Doina Precup

We establish an optimal sample complexity of $O(\epsilon^{-2})$ for obtaining an $\epsilon$-optimal global policy using a single-timescale actor-critic (AC) algorithm in infinite-horizon discounted Markov decision processes (MDPs) with…

Machine Learning · Computer Science 2026-05-08 Navdeep Kumar , Tehila Dahan , Lior Cohen , Ananyabrata Barua , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor