中文
相关论文

相关论文: Settling the Variance of Multi-Agent Policy Gradie…

200 篇论文

In this paper, we propose a maximum mutual information (MMI) framework for multi-agent reinforcement learning (MARL) to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the mutual information…

多智能体系统 · 计算机科学 2020-06-05 Woojun Kim , Whiyoung Jung , Myungsik Cho , Youngchul Sung

Ranking is a fundamental and widely studied problem in scenarios such as search, advertising, and recommendation. However, joint optimization for multi-scenario ranking, which aims to improve the overall performance of several ranking…

人工智能 · 计算机科学 2018-09-18 Jun Feng , Heng Li , Minlie Huang , Shichen Liu , Wenwu Ou , Zhirong Wang , Xiaoyan Zhu

Markov games (MGs) and multi-agent reinforcement learning (MARL) are studied to model decision making in multi-agent systems. Traditionally, the objective in MG and MARL has been risk-neutral, i.e., agents are assumed to optimize a…

计算机科学与博弈论 · 计算机科学 2024-06-11 Hafez Ghaemi , Shirin Jamshidi , Mohammad Mashreghi , Majid Nili Ahmadabadi , Hamed Kebriaei

In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods…

机器学习 · 计算机科学 2018-06-15 Matteo Papini , Damiano Binaghi , Giuseppe Canonaco , Matteo Pirotta , Marcello Restelli

Reinforcement learning (RL) has emerged as a powerful approach for tackling complex problems. The recent introduction of multi-objective reinforcement learning (MORL) has further expanded the scope of RL by enabling agents to make…

机器学习 · 计算机科学 2023-10-26 Florian Felten , Daniel Gareev , El-Ghazali Talbi , Grégoire Danoy

This paper aims to mitigate straggler effects in synchronous distributed learning for multi-agent reinforcement learning (MARL) problems. Stragglers arise frequently in a distributed learning system, due to the existence of various system…

机器学习 · 计算机科学 2021-01-08 Baoqian Wang , Junfei Xie , Nikolay Atanasov

Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g.,…

机器学习 · 计算机科学 2021-04-30 Kaiqing Zhang , Zhuoran Yang , Tamer Başar

The empirical success of multi-agent reinforcement learning (MARL) has motivated the search for more efficient and scalable algorithms for large scale multi-agent systems. However, existing state-of-the-art algorithms do not fully exploit…

多智能体系统 · 计算机科学 2025-10-14 Shahbaz P Qadri Syed , He Bai

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

机器学习 · 计算机科学 2026-03-03 Daniel Ritter , Owen Oertell , Bradley Guo , Jonathan Chang , Kianté Brantley , Wen Sun

Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual, iterative refinement of algorithmic baselines. Recently, evolutionary coding agents powered by…

计算机科学与博弈论 · 计算机科学 2026-05-11 Zun Li , John Schultz , Daniel Hennes , Marc Lanctot

In this paper, we propose World Model Policy Gradient (WMPG), an approach to reduce the variance of policy gradient estimates using learned world models (WM's). In WMPG, a WM is trained online and used to imagine trajectories. The imagined…

机器学习 · 统计学 2020-10-30 Michal Nauman , Floris Den Hengst

Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems where we seek to recover both policies for our agents and reward functions that promote expert-like…

多智能体系统 · 计算机科学 2020-02-26 Wonseok Jeon , Paul Barde , Derek Nowrouzezahrai , Joelle Pineau

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function…

Discovering successful coordinated behaviors is a central challenge in Multi-Agent Reinforcement Learning (MARL) since it requires exploring a joint action space that grows exponentially with the number of agents. In this paper, we propose…

机器学习 · 计算机科学 2021-10-14 Ammar Fayad , Majd Ibrahim

In real-world multi-agent reinforcement learning (MARL) applications, agents may not have perfect state information (e.g., due to inaccurate measurement or malicious attacks), which challenges the robustness of agents' policies. Though…

机器学习 · 计算机科学 2023-08-01 Sihong He , Songyang Han , Sanbao Su , Shuo Han , Shaofeng Zou , Fei Miao

Using Machine Learning (ML) techniques for the next generation wireless networks have shown promising results in the recent years, due to high learning and adaptation capability of ML algorithms. More specifically, ML techniques have been…

网络与互联网体系结构 · 计算机科学 2021-10-18 Pedro Enrique Iturria Rivera , Melike Erol-Kantarci

In this paper, we propose a new mutual information framework for multi-agent reinforcement learning to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the simultaneous mutual information…

多智能体系统 · 计算机科学 2023-03-02 Woojun Kim , Whiyoung Jung , Myungsik Cho , Youngchul Sung

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

机器学习 · 计算机科学 2024-07-30 Jayesh Singla , Ananye Agarwal , Deepak Pathak

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

机器学习 · 计算机科学 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous…

人工智能 · 计算机科学 2025-05-16 Tailia Malloy , Tim Klinger , Miao Liu , Matthew Riemer , Gerald Tesauro , Chris R. Sims