English
Related papers

Related papers: Error Controlled Actor-Critic

200 papers

In value-based reinforcement learning (RL), unlike in supervised learning, the agent faces not a single, stationary, approximation problem, but a sequence of value prediction problems. Each time the policy improves, the nature of the…

Machine Learning · Computer Science 2021-01-05 Will Dabney , André Barreto , Mark Rowland , Robert Dadashi , John Quan , Marc G. Bellemare , David Silver

This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy…

Machine Learning · Computer Science 2019-11-20 Wesley Suttle , Zhuoran Yang , Kaiqing Zhang , Zhaoran Wang , Tamer Basar , Ji Liu

Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a learned value function. However, learned value models are…

Machine Learning · Computer Science 2026-04-14 Zikang Shan , Han Zhong , Liwei Wang , Li Zhao

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…

Machine Learning · Computer Science 2019-04-09 Ishan Durugkar , Matthew Hausknecht , Adith Swaminathan , Patrick MacAlpine

We analyze the global convergence of the single-timescale actor-critic (AC) algorithm for the infinite-horizon discounted Markov Decision Processes (MDPs) with finite state spaces. To this end, we introduce an elegant analytical framework…

Machine Learning · Computer Science 2025-06-05 Navdeep Kumar , Priyank Agrawal , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing…

Machine Learning · Computer Science 2017-03-06 Dzmitry Bahdanau , Philemon Brakel , Kelvin Xu , Anirudh Goyal , Ryan Lowe , Joelle Pineau , Aaron Courville , Yoshua Bengio

Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-world applications, agents must succeed in one-shot settings…

Computation and Language · Computer Science 2026-04-02 Shuli Jiang , Zhaoyang Zhang , Yi Zhang , Shuo Yang , Wei Xia , Stefano Soatto

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is…

Robotics · Computer Science 2020-07-16 Minghao Han , Lixian Zhang , Jun Wang , Wei Pan

In the context of Federated Reinforcement Learning (FRL), applying Proximal Policy Optimization (PPO) faces challenges related to the update order of its actor and critic due to the aggregation step occurring between successive iterations.…

Machine Learning · Computer Science 2025-06-03 Zhijie Xie , Shenghui Song

Policy optimization methods remain a powerful workhorse in empirical Reinforcement Learning (RL), with a focus on neural policies that can easily reason over complex and continuous state and/or action spaces. Theoretical understanding of…

Machine Learning · Computer Science 2021-03-23 Fei Feng , Wotao Yin , Alekh Agarwal , Lin F. Yang

Off-policy actor-critic methods in reinforcement learning train a critic with temporal-difference updates and use it as a learning signal for the policy (actor). This design typically achieves higher sample efficiency than purely on-policy…

Machine Learning · Computer Science 2026-01-05 Uğurcan Özalp

Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing…

Multiagent Systems · Computer Science 2026-02-16 Yizhou Zhang , Eric Mazumdar

Deep actor-critic algorithms have reached a level where they influence everyday life. They are a driving force behind continual improvement of large language models through user feedback. However, their deployment in physical systems is not…

Machine Learning · Computer Science 2025-11-27 Bahareh Tasdighi , Manuel Haussmann , Yi-Shan Wu , Andres R. Masegosa , Melih Kandemir

Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value…

Machine Learning · Statistics 2017-03-14 Yemi Okesanjo , Victor Kofia

Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of…

Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or give up personalization altogether by training a single…

Machine Learning · Computer Science 2026-05-15 Leo Muxing Wang , Pengkun Yang , Lili Su

Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms typically causes immediate drops in performance. We provide evidence consistent…

Machine Learning · Computer Science 2026-03-02 Nathan Samuel de Lara , Florian Shkurti

In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSAC) algorithm, which…

Machine Learning · Computer Science 2021-06-14 Jingliang Duan , Yang Guan , Shengbo Eben Li , Yangang Ren , Bo Cheng

We revisit the Karagiannidis-Lioumpas (KL) approximation of the Q-function by optimizing its coefficients in terms of absolute error, relative error and total error. For minimizing the maximum absolute/relative error, we describe the…

Signal Processing · Electrical Eng. & Systems 2021-01-20 Islam M. Tanash , Taneli Riihonen

By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…

Machine Learning · Computer Science 2023-12-01 Jared Markowitz , Jesse Silverberg , Gary Collins
‹ Prev 1 8 9 10 Next ›