UneVEn: Universal value exploration for multi-agent reinforcement learning

UneVEn: Universal value exploration for multi-agent reinforcement learning

VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solvi...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Gupta, T, Mahajan, A, Peng, B, Boehmer, W, Whiteson, S
Format:	Conference item
Sprog:	English
Udgivet:	PMLR 2021

Lignende værker

Randomized entity-wise factorization for multi-agent reinforcement learning
af: Iqbal, S, et al.
Udgivet: (2021)

Multi-agent common knowledge reinforcement learning
af: de Witt, C, et al.
Udgivet: (2019)

MAVEN: Multi-Agent Variational Exploration
af: Mahajan, A, et al.
Udgivet: (2019)

RODE: learning roles to decompose multi−agent tasks
af: Wang, T, et al.
Udgivet: (2021)

Weighted QMIX: Expanding monotonic value function factorisation for deep multi−agent reinforcement learning
af: Rashid, T, et al.
Udgivet: (2020)

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning
af: Castellini, J, et al.
Udgivet: (2021)

Exploration and value function factorisation in single and multi-agent reinforcement learning
af: Rashid, T
Udgivet: (2021)

Monotonic value function factorisation for deep multi-agent reinforcement learning
af: Rashid, T, et al.
Udgivet: (2020)

Tesseract: tensorised actors for multi−agent reinforcement learning
af: Mahajan, A, et al.
Udgivet: (2021)

Bayesian action decoder for deep multi-agent reinforcement learning
af: Whiteson, S
Udgivet: (2019)

QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning
af: Rashid, T, et al.
Udgivet: (2018)

Learning to communicate with Deep multi-agent reinforcement learning
af: Foerster, J, et al.
Udgivet: (2016)

Deep residual reinforcement learning
af: Zhang, S, et al.
Udgivet: (2020)

Stabilising experience replay for deep multi-agent reinforcement learning
af: Foerster, J, et al.
Udgivet: (2017)

The challenges and future perspective of Kenaf Wo-ven reinforcement in thermoset polymer composites in Malaysia: a review
af: Lee, Ching Hao, et al.
Udgivet: (2021)

Improving single and multi-agent deep reinforcement learning methods
af: Gupta, T
Udgivet: (2023)

End-to-end deep reinforcement learning for multi-agent collaborative exploration
af: Chen, Zichen, et al.
Udgivet: (2021)

Infrastructure, sustainability and unevenness : exploring marginalization in Mexico
af: Quezada Medina, Jessica.
Udgivet: (2020)

Regularized Softmax Deep Multi−Agent Q−Learning
af: Pan, L, et al.
Udgivet: (2022)

Towards coordinated multi-agent exploration problem via segmentation and reinforcement learning
af: Chen, Zichen
Udgivet: (2020)

Deep multi-agent reinforcement learning
af: Foerster, J
Udgivet: (2018)

Deep reinforcement learning to multi-agent deep reinforcement learning
af: Samieiyeganeh, Mehdi, et al.
Udgivet: (2022)

Transient non−stationarity and generalisation in deep reinforcement learning
af: Igl, M, et al.
Udgivet: (2021)

VIREL: A variational inference framework for reinforcement learning
af: Fellows, M, et al.
Udgivet: (2019)

Learning multi-agent competitive games with reinforcement learning
af: Neo, Yong Tai
Udgivet: (2022)

Cooperation and Fairness in Multi-Agent Reinforcement Learning
af: Aloor, Jasmine, et al.
Udgivet: (2024)

Multi-Agent Reinforcement Learning for Autonomous Robotics
af: Vincent, Caroline R.
Udgivet: (2024)

Data-efficient multi-agent reinforcement learning
af: Wong, Reuben Yuh Sheng
Udgivet: (2022)

Hierarchical multi-agent reinforcement learning with options
af: Ang, Wan Qi
Udgivet: (2021)

Europe's uneven development
af: Hennig, BD, et al.
Udgivet: (2015)

Multi-Agent Reinforcement Learning For Swarm Robots Formation
af: Bujang, Christina
Udgivet: (2021)

Multi agent reinforcement learning for UAV collision avoidance
af: Abdul Hamid, Nor Asilah Wati, et al.
Udgivet: (2024)

Analyzing Multi-Agent Reinforcement Learning and Coevolution in Cybersecurity
af: Turner, Matthew, et al.
Udgivet: (2022)

Coordination and communication in deep multi-agent reinforcement learning
af: Schroeder de Witt, CA
Udgivet: (2021)

Une expérience rhétorique
Udgivet: (2017)

Exploring Memory in Reinforcement-Learned Agents for Smarter Lateral Movement
af: Johnson Schofield, Catherine
Udgivet: (2024)

Augmented realities and uneven geographies: exploring the geo-linguistic contours of the web
af: Graham, M
Udgivet: (2013)

Uneven paths of development : innovation and learning in Asia and Africa /
af: 289462 Oyelaran-Oyeyinka, Banji, et al.
Udgivet: (2008)

Evolutionary transfer learning for complex multi-agent reinforcement learning systems
af: Hou, Yaqing
Udgivet: (2017)

Cooperative reinforcement learning in topology-based multi-agent systems
af: Xiao, Dan, et al.
Udgivet: (2014)