Reinforcement Learning with Non-uniform State Representations for Adaptive Search.
Sandeep ManjannaHerke van HoofGregory DudekPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- optimal policy
- markov decision processes
- learning problems
- reinforcement learning algorithms
- control problems
- learning capabilities
- multi agent
- learning process
- data mining
- dynamic programming
- transfer learning
- learning classifier systems
- action selection
- reward function
- knowledge base
- data sets