Mutli-agent consensus under communication failure using Actor-Critic Reinforcement Learning.
Harikumar KandathSenthilnath JayaveluSuresh SundaramPublished in: SSCI (2018)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- action selection
- multi agent
- reinforcement learning algorithms
- policy gradient
- approximate dynamic programming
- learning agent
- optimal control
- neuro fuzzy
- gradient method
- function approximation
- reward function
- multi agent systems
- single agent
- state action
- policy iteration
- control problems
- partially observable
- policy gradient methods
- learning capabilities
- multiple agents
- model free
- markov decision processes
- reinforcement learning methods
- state space
- machine learning
- decision making
- markov decision process
- action space
- temporal difference learning
- dynamic programming
- least squares
- infinite horizon
- rl algorithms
- learning algorithm
- natural actor critic
- adaptive control