RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization.
Siqi ShenChennan MaChao LiWeiquan LiuYongquan FuSongzhu MeiXinwang LiuCheng WangPublished in: NeurIPS (2023)
Keyphrases
- multi agent reinforcement learning
- risk sensitive
- optimal control
- markov decision processes
- utility function
- reinforcement learning
- multi agent
- stochastic games
- model free
- control policies
- learning agents
- optimality criterion
- cooperative
- multi agent learning
- multi agent systems
- expected utility
- decision theoretic
- artificial intelligence
- markov decision problems
- average cost
- infinite horizon
- neural network
- mobile robot
- dynamic programming
- learning agent
- optimal policy
- decision makers
- bayesian networks
- search space