Reinforcement Learning with Non-uniform State Representations for Adaptive Search.
Sandeep ManjannaHerke van HoofGregory DudekPublished in: SSRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- optimal policy
- multi agent reinforcement learning
- control problems
- markov decision processes
- optimal control
- perceptual aliasing
- reinforcement learning algorithms
- learning algorithm
- machine learning
- supervised learning
- semi supervised
- decision trees
- action selection
- temporal difference
- learning capabilities
- data mining
- data sets