Reinforcement learning with value advice.
Mayank DaswaniPeter SunehagMarcus HutterPublished in: ACML (2014)
Keyphrases
- reinforcement learning
- function approximation
- state space
- robotic control
- markov decision processes
- reinforcement learning algorithms
- learning algorithm
- multi agent
- supervised learning
- temporal difference
- model free
- optimal policy
- machine learning
- learning process
- neural network
- multi agent reinforcement learning
- partially observable
- decision making
- dynamical systems
- bayesian networks
- learning tasks
- artificial intelligence
- optimal control
- learning classifier systems
- databases
- data mining
- real world
- multi agent systems
- stochastic approximation
- dynamic programming
- policy search
- perceptual aliasing
- expert systems