English
Related papers

Related papers: Policy Gradient With Value Function Approximation …

200 papers

Decentralized Actor-Critic (AC) algorithms have been widely utilized for multi-agent reinforcement learning (MARL) and have achieved remarkable success. Apart from its empirical success, the theoretical convergence property of decentralized…

Machine Learning · Computer Science 2023-01-31 Qijun Luo , Xiao Li

Most works on multi-agent reinforcement learning focus on scenarios where the state of the environment is fully observable. In this work, we consider a cooperative policy evaluation task in which agents are not assumed to observe the…

Machine Learning · Computer Science 2023-05-17 Mert Kayaalp , Fatima Ghadieh , Ali H. Sayed

[Zhang, ICML 2018] provided the first decentralized actor-critic algorithm for multi-agent reinforcement learning (MARL) that offers convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We…

Machine Learning · Computer Science 2021-02-22 Antoine Grosnit , Desmond Cai , Laura Wynter

Multi-Agent Policy Gradient (MAPG) has made significant progress in recent years. However, centralized critics in state-of-the-art MAPG methods still face the centralized-decentralized mismatch (CDM) issue, which means sub-optimal actions…

Multiagent Systems · Computer Science 2024-01-17 Xingzhou Lou , Junge Zhang , Timothy J. Norman , Kaiqi Huang , Yali Du

Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) are known to be NEXP-Complete and intractable to solve. However, for problems such as cooperative navigation, obstacle avoidance, and formation control, basic…

Multiagent Systems · Computer Science 2025-06-05 Alex DeWeese , Guannan Qu

Recent multi-agent actor-critic methods have utilized centralized training with decentralized execution to address the non-stationarity of co-adapting agents. This training paradigm constrains learning to the centralized phase such that…

Multiagent Systems · Computer Science 2019-10-09 Kevin Corder , Manuel M. Vindiola , Keith Decker

Decision making in multi-agent systems (MAS) is a great challenge due to enormous state and joint action spaces as well as uncertainty, making centralized control generally infeasible. Decentralized control offers better scalability and…

Artificial Intelligence · Computer Science 2019-01-28 Thomy Phan , Kyrill Schmid , Lenz Belzner , Thomas Gabor , Sebastian Feld , Claudia Linnhoff-Popien

In this paper, a novel Multi-agent Reinforcement Learning (MARL) approach, Multi-Agent Continuous Dynamic Policy Gradient (MACDPP) was proposed to tackle the issues of limited capability and sample efficiency in various scenarios controlled…

Systems and Control · Electrical Eng. & Systems 2023-09-27 Chenyang Miao , Yunduan Cui , Huiyun Li , Xinyu Wu

Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized policies for such tasks using sub-optimal demonstration. To…

Artificial Intelligence · Computer Science 2021-08-20 Peixi Peng , Junliang Xing

We present decentralized rollout sampling policy iteration (DecRSPI) - a new algorithm for multi-agent decision problems formalized as DEC-POMDPs. DecRSPI is designed to improve scalability and tackle problems that lack an explicit model.…

Artificial Intelligence · Computer Science 2012-03-19 Feng Wu , Shlomo Zilberstein , Xiaoping Chen

Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on good individual actions, but on selecting compatible actions…

Machine Learning · Computer Science 2026-02-24 Nikunj Gupta , James Zachary Hare , Jesse Milzman , Rajgopal Kannan , Viktor Prasanna

Attention mechanisms excel at learning sequential patterns by discriminating data based on relevance and importance. This provides state-of-the-art performance in advanced generative artificial intelligence models. This paper applies this…

Systems and Control · Electrical Eng. & Systems 2026-03-24 Turki Bin Mohaya , Peter Seiler

This paper addresses the challenge of allocating heterogeneous resources among multiple agents in a decentralized manner. Our proposed method, Liquid-Graph-Time Clustering-IPPO, builds upon Independent Proximal Policy Optimization (IPPO) by…

Machine Learning · Statistics 2026-02-12 Antonio Marino , Esteban Restrepo , Claudio Pacchierotti , Paolo Robuffo Giordano

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

Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study…

Machine Learning · Computer Science 2021-12-08 Siliang Zeng , Tianyi Chen , Alfredo Garcia , Mingyi Hong

This paper presents a data-driven approach for multi-robot coordination in partially-observable domains based on Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) and macro-actions (MAs). Dec-POMDPs provide a general…

Multiagent Systems · Computer Science 2017-08-21 Miao Liu , Kavinayan Sivakumar , Shayegan Omidshafiei , Christopher Amato , Jonathan P. How

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…

We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from…

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

In this paper, we introduce an actor-critic algorithm called Deep Value Model Predictive Control (DMPC), which combines model-based trajectory optimization with value function estimation. The DMPC actor is a Model Predictive Control (MPC)…

Machine Learning · Computer Science 2019-10-09 Farbod Farshidian , David Hoeller , Marco Hutter