Reinforcement Learning for Heterogeneous Teams with PALO Bounds.
Roi CerenPrashant DoshiKeyang HePublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- team composition
- upper bound
- multi agent
- function approximation
- model free
- cooperative
- lower bound
- robotic control
- state space
- learning algorithm
- robocup soccer
- reinforcement learning algorithms
- learning process
- machine learning
- globally distributed
- upper and lower bounds
- policy search
- tight bounds
- worst case
- heterogeneous networks
- temporal difference
- learning problems
- markov decision processes
- neural network
- solve complex tasks
- data sets
- optimal policy
- supervised learning
- databases