Autonomous Reinforcement Learning with Experience Replay for Humanoid Gait Optimization.
Pawel WawrzynskiPublished in: INNS-WC (2012)
Keyphrases
- reinforcement learning
- optimization algorithm
- autonomous learning
- cooperative
- optimization problems
- motion capture
- global optimization
- optimization process
- multi agent
- gait analysis
- learning capabilities
- function approximation
- combinatorial optimization
- human recognition
- robotic systems
- degrees of freedom
- optimization method
- optimal policy
- dynamic environments
- state space
- objective function