Curiosity-Driven Reinforcement Learning with Homeostatic Regulation.
Ildefons Magrans de AbrilRyota KanaiPublished in: IJCNN (2018)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- markov decision processes
- temporal difference
- data driven
- learning agents
- model free
- real world
- robotic control
- multi agent reinforcement learning
- stochastic approximation
- control problems
- optimal policy
- supervised learning
- state space
- active learning
- multi agent
- information systems
- real time
- transfer learning
- action selection
- learning agent
- learning algorithm
- temporal difference learning
- genetic algorithm
- information retrieval