Statistics and Samples in Distributional Reinforcement Learning.
Mark RowlandRobert DadashiSaurabh KumarRémi MunosMarc G. BellemareWill DabneyPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- training samples
- data sets
- reinforcement learning algorithms
- machine learning
- function approximation
- optimal policy
- temporal difference
- dynamic programming
- training set
- multi agent
- model free
- learning algorithm
- active learning
- evolutionary algorithm
- optimal control
- statistical modeling
- small sample