Proximal Policy Optimization with Relative Pearson Divergence.
Taisuke KobayashiPublished in: ICRA (2021)
Keyphrases
- global optimization
- optimization algorithm
- optimization problems
- optimization process
- discrete optimization
- optimization model
- constrained optimization
- optimization methods
- optimization method
- markov decision processes
- regression model
- optimal policy
- decision making
- information retrieval
- real time
- evolution strategy
- optimal design
- robust optimization
- direct search
- correlation coefficient
- search space
- search algorithm
- multi agent
- learning algorithm
- neural network