Competitiveness of MAP-Elites against Proximal Policy Optimization on locomotion tasks in deterministic simulations.
Szymon BrychAntoine CullyPublished in: CoRR (2020)
Keyphrases
- optimization algorithm
- direct search
- robotic systems
- multiple tasks
- mobile robot
- optimization problems
- optimization process
- data sets
- global optimization
- numerical simulations
- constrained optimization
- black box
- degrees of freedom
- optimization method
- transfer learning
- optimal policy
- reinforcement learning
- learning algorithm