Increasing the Action Gap: New Operators for Reinforcement Learning.
Marc G. BellemareGeorg OstrovskiArthur GuezPhilip S. ThomasRémi MunosPublished in: AAAI (2016)
Keyphrases
- reinforcement learning
- action selection
- partially observable domains
- action space
- function approximation
- multi agent
- transition model
- optimal policy
- reward shaping
- morphological operators
- state and action spaces
- temporal difference
- machine learning
- human actions
- markov decision processes
- learning algorithm
- partially observable
- markov decision process
- action recognition
- state action
- state space
- decision making
- computer vision
- robotic control