Trustable Policy Collaboration Scheme for Multi-Agent Stigmergic Reinforcement Learning.
Xing XuRongpeng LiZhifeng ZhaoHonggang ZhangPublished in: IEEE Commun. Lett. (2022)
Keyphrases
- reinforcement learning
- multi agent
- optimal policy
- policy making
- policy search
- action selection
- cooperative
- markov decision problems
- approximate dynamic programming
- function approximation
- state space
- markov decision process
- partially observable
- policy evaluation
- partially observable environments
- control policy
- multi agent reinforcement learning
- partially observable domains
- markov decision processes
- reward function
- machine learning
- actor critic
- multiagent systems
- policy gradient
- average reward
- single agent
- action space
- policy iteration
- reinforcement learning algorithms
- learning algorithm
- state and action spaces
- learning process
- learning agents
- state action
- decision problems
- long run
- infinite horizon
- complex systems
- finite state
- continuous state spaces
- control policies
- rl algorithms