RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents

RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents

Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness o...

Saved in:

書目詳細資料
Main Authors:	QIU, Wei, WANG, Xinrun, YU, Runsheng, HE, Xu, WANG, Rundong, AN, Bo, OBRAZTSOVA, Svetlana, RABINOVICH, Zinovi
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2021
主題:	Artificial Intelligence and Robotics Theory and Algorithms
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/9137 https://ink.library.smu.edu.sg/context/sis_research/article/10140/viewcontent/NeurIPS_2021_rmix__pvoa.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

Learning to collaborate in multi-module recommendation via multi-agent reinforcement learning without communication
由: HE, Xu, et al.
出版: (2020)

Learning expensive coordination: An event-based deep RL approach
由: YU, Runsheng, et al.
出版: (2020)

PRUDEX-Compass: Towards systematic evaluation of reinforcement learning in financial markets
由: SUN, Shuo, et al.
出版: (2023)

Transition-informed reinforcement learning for large-scale Stackelberg mean-field games.
由: LI, Pengdeng, et al.
出版: (2024)

Understanding Sequential Decisions via Inverse Reinforcement Learning
由: LIU, Siyuan, et al.
出版: (2013)

Motivated learning as an extension of reinforcement learning
由: STARZYK, Janusz, et al.
出版: (2010)

Who should pay the cost: A game-theoretic model for government subsidized investments to improve national cybersecurity
由: WANG, Xinrun, et al.
出版: (2019)

Reinforcement Nash Equilibrium Solver
由: WANG, Xinrun, et al.
出版: (2024)

Towards efficient cooperation within learning agents
由: Wang, Rundong
出版: (2023)

Integrating motivated learning and k-winner-take-all to coordinate multi-agent reinforcement learning
由: TENG, Teck-Hou, et al.
出版: (2014)

Correlated learning for aggregation systems
由: VERMA, Tanvi, et al.
出版: (2019)

Controlling type confounding in ad hoc teamwork with instance-wise teammate feedback rectification
由: XING, Dong, et al.
出版: (2023)

Task similarity aware meta learning: Theory-inspired improvement on MAML
由: ZHOU, Pan, et al.
出版: (2021)

Inverse factorized soft Q-Learning for cooperative multi-agent imitation learning
由: BUI, The Viet, et al.
出版: (2024)

Decentralized multi-agent reinforcement learning in average-reward dynamic DCOPs
由: Nguyen, Duc Thien, et al.
出版: (2014)

Decentralized multi-agent reinforcement learning in average-reward dynamic DCOPs
由: NGUYEN, Duc Thien, et al.
出版: (2014)

EarnHFT: Efficient hierarchical reinforcement learning for high frequency trading
由: QIN, Molei, et al.
出版: (2024)

Self-organizing neural architectures and multi-agent cooperative reinforcement learning
由: Xiao, Dan
出版: (2010)

Constrained reinforcement learning in hard exploration problems
由: PATHMANATHAN, Pankayaraj, et al.
出版: (2023)

Learning to send reinforcements: Coordinating multi-agent dynamic police patrol dispatching and rescheduling via reinforcement learning
由: JOE, Waldy, et al.
出版: (2023)

MacroHFT : Memory augmented context-aware reinforcement learning on high frequency trading
由: ZONG, Chuqiao, et al.
出版: (2024)

Stop nuclear smuggling through efficient container inspection
由: WANG, Xinrun, et al.
出版: (2017)

Credit assignment in multiagent reinforcement learning for large agent population
由: SINGH, Arambam James
出版: (2021)

DO-GAN: A double oracle framework for generative adversarial networks
由: AUNG, Aye Phyu Phye, et al.
出版: (2022)

Constrained multiagent reinforcement learning for large agent population
由: LING, Jiajing, et al.
出版: (2022)

Integrating motivated learning and k-winner-take-all to coordinate multi-agent reinforcement learning
由: TENG, Teck-Hou, et al.
出版: (2014)

Difference of convex functions programming for policy optimization in reinforcement learning
由: KUMAR, Akshat
出版: (2024)

Offline RL with discrete proxy representations for generalizability in POMDPs
由: GU, Pengjie, et al.
出版: (2023)

Deep Reinforcement Learning With Explicit Context Representation
由: Munguia-Galeano, Francisco, et al.
出版: (2023)

Reinforcement learning with maskable stock representation for portfolio management in customizable stock pools
由: ZHANG, Wentao, et al.
出版: (2024)

RMM: Reinforced memory management for class-incremental learning
由: LIU, Yaoyao, et al.
出版: (2021)

Multi-agent collaborative exploration through graph-based deep reinforcement learning
由: LUO, Tianze, et al.
出版: (2019)

End-to-end deep reinforcement learning for multi-agent collaborative exploration
由: CHEN, Zichen, et al.
出版: (2019)

Constrained multiagent reinforcement learning for large agent population
由: LING, Jiajing, et al.
出版: (2023)

Online control of adaptive large neighborhood search using deep reinforcement learning
由: REIJNEN, Reijnen, et al.
出版: (2024)

Multi-agent reinforcement learning for complex sequential decision-making
由: Qiu, Wei
出版: (2024)

CFR-MIX: Solving imperfect information extensive-form games with combinatorial action space
由: LI, Shuxin, et al.
出版: (2021)

Algorithms for a fast and reliable color-based global vision for FIRA MiRoSot large league soccer robot system
由: Gunay, Noel S.
出版: (2010)

Neighborhood cooperative multiagent reinforcement learning for adaptive traffic signal control in epidemic regions
由: ZHANG, Chengwei, et al.
出版: (2022)

Continual learning, fast and slow
由: PHAM, Quang Anh, et al.
出版: (2024)