Reinforcement learning in decentralized stochastic control systems with partial history sharing.
Jalal ArabneydiAditya MahajanPublished in: ACC (2015)
Keyphrases
- reinforcement learning
- control system
- direct policy search
- control policies
- multi agent
- stochastic approximation
- learning automata
- optimal policy
- robotic control
- monte carlo
- peer to peer
- function approximation
- state space
- temporal difference
- information sharing
- multiagent reinforcement learning
- learning algorithm
- model free
- data sharing
- markov decision processes
- cooperative
- distributed systems
- transfer learning
- control strategies
- sufficient conditions
- dynamic programming
- machine learning
- control strategy
- decision making
- industrial automation
- continuous state spaces
- multi agent reinforcement learning
- supervised learning
- control problems
- reinforcement learning algorithms
- control law
- knowledge sharing