Soft Actor-Critic with Cross-Entropy Policy Optimization.
Zhenyang ShiSurya P. N. SinghPublished in: CoRR (2021)
Keyphrases
- cross entropy
- actor critic
- policy gradient
- reinforcement learning
- approximate dynamic programming
- neuro fuzzy
- optimal control
- policy iteration
- temporal difference
- gradient method
- log likelihood
- average reward
- maximum likelihood
- function approximation
- markov decision processes
- evaluation metrics
- reinforcement learning algorithms
- optimal policy
- optimization algorithm
- dynamic programming
- step size
- probabilistic model
- model selection
- state space
- neural network