Layered Relative Entropy Policy Search.
Navid Hoseini IzadiMaziar PalhangMehran SafayaniPublished in: Knowl. Based Syst. (2021)
Keyphrases
- relative entropy
- policy search
- reinforcement learning
- information theoretic
- information theory
- covariance matrix
- log likelihood
- continuous state
- mutual information
- dynamic programming
- reinforcement learning algorithms
- mahalanobis distance
- reward function
- maximum entropy
- kullback leibler divergence
- bregman divergences
- partially observable markov decision processes
- policy gradient
- neural network