Task Feasibility Maximization Using Model-Free Policy Search and Model-Based Whole-Body Control.
Ryan LoberOlivier SigaudVincent PadoisPublished in: Frontiers Robotics AI (2020)
Keyphrases
- model free
- policy search
- reinforcement learning algorithms
- reinforcement learning
- temporal difference
- function approximation
- policy iteration
- adaptive control
- control system
- reinforcement learning methods
- control policy
- continuous state
- optimal control
- robotic systems
- control strategies
- action selection
- least squares
- support vector machine
- state space