G-Learning: Taming the Noise in Reinforcement Learning via Soft Updates.
Roy FoxAri PakmanNaftali TishbyPublished in: CoRR (2015)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- learning problems
- autonomous learning
- online learning
- learning systems
- prior knowledge
- learning agents
- background knowledge
- markov decision processes
- function approximation
- learning capabilities
- robot control
- active learning
- learning analytics
- inductive inference
- partially observable
- function approximators
- learned knowledge
- multi agent systems
- evolutionary learning