Introspective Reinforcement Learning and Learning from Demonstration.
Mao LiTim BrysDaniel KudenkoPublished in: AAMAS (2018)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning problems
- robotic control
- optimal control
- state space
- reinforcement learning methods
- temporal difference
- action selection
- model free
- neural network
- control problems
- machine learning
- learning algorithm
- markov decision processes
- transfer learning
- information systems
- genetic algorithm
- case study
- database
- supervised learning
- learning agents
- temporal difference learning
- autonomous learning
- expert systems