Marginalized Operators for Off-policy Reinforcement Learning.
Yunhao TangMark RowlandRémi MunosMichal ValkoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- learning process
- model free
- function approximators
- graph kernels
- state space
- markov decision processes
- reinforcement learning methods
- machine learning
- temporal difference
- morphological operators
- data sets
- policy search
- relational reinforcement learning
- robot control
- action selection
- real time
- mathematical morphology
- optimal policy
- building blocks
- sufficient conditions
- dynamic programming
- multiscale
- information systems
- social networks
- learning algorithm
- neural network