Decomposition-based Multi-Agent Distributional Reinforcement Learning for Task-Oriented UAV Collaboration with Noisy Rewards.
Wei GengBaidi XiaoRongpeng LiNing WeiZhifeng ZhaoHonggang ZhangPublished in: WCSP (2023)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- state space
- markov decision processes
- reinforcement learning algorithms
- co occurrence
- information sharing
- temporal difference
- learning algorithm
- model free
- learning process
- machine learning
- cooperative
- action selection
- optimal policy
- optimal control
- reinforcement learning agents
- noisy data
- transfer learning
- dynamic programming
- knowledge sharing
- learning agents
- single agent
- decomposition method
- description language
- learning classifier systems
- coalition formation
- total reward
- path planning
- multiagent systems
- collaborative learning
- knowledge management
- multi agent systems
- multi agent environments
- traffic signal control
- state abstraction
- control policy
- unmanned aerial vehicles
- function approximators
- policy iteration
- markov decision process
- complex domains
- noisy environments
- multiple agents
- learning community
- control algorithm
- dynamic environments