Accelerating Reinforcement Learning with Suboptimal Guidance.
Eivind BøhnSigne MoeTor Arne JohansenPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- markov decision processes
- multi agent
- optimal policy
- direct policy search
- reinforcement learning algorithms
- computationally efficient
- learning algorithm
- machine learning
- temporal difference
- real time
- multi agent reinforcement learning
- database
- optimal control
- case study
- action selection
- robotic control
- reinforcement learning methods
- temporal difference learning
- learning agents
- locally optimal
- databases
- neural network
- information systems
- decision making
- active learning
- artificial neural networks