Estimating Probability Distribution with Q-learning for Biped Gait Generation and Optimization.
Lingyun HuChangjiu ZhouZengqi SunPublished in: IROS (2006)
Keyphrases
- probability distribution
- biped robot
- reinforcement learning
- cooperative
- global optimization
- optimization problems
- function approximation
- optimization algorithm
- random variables
- multi agent
- state space
- optimization method
- learning algorithm
- control strategy
- biologically inspired
- gait recognition
- action selection
- gait analysis
- neural network
- human gait recognition
- biped walking