Curiosity-driven reinforcement learning with homeostatic regulation.
Ildefons Magrans de AbrilRyota KanaiPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- data driven
- learning process
- dynamic programming
- markov decision processes
- machine learning
- policy search
- reinforcement learning algorithms
- model free
- state space
- optimal policy
- robotic control
- temporal difference
- optimal control
- transfer learning
- knowledge base
- learning algorithm
- control system
- artificial neural networks
- multiscale
- learning agents
- decision making