Biological Robot Arm Motion through Reinforcement Learning.
Jun IzawaToshiyuki KondoKoji ItoPublished in: ICRA (2002)
Keyphrases
- robot arm
- motion planning
- inverse kinematics
- reinforcement learning
- end effector
- natural actor critic
- position and orientation
- joint angles
- control strategies
- mobile robot
- real robot
- degrees of freedom
- humanoid robot
- control law
- function approximation
- skill learning
- nonlinear systems
- adaptive control
- motion estimation
- optimal control
- machine learning
- dynamic programming
- reinforcement learning algorithms
- neural network
- real world
- state space
- optimal policy
- model free
- complex systems
- markov decision processes
- real time
- multi robot