Causal Policy Gradient for Whole-Body Mobile Manipulation.
Jiaheng HuPeter StoneRoberto Martín-MartínPublished in: Robotics: Science and Systems (2023)
Keyphrases
- policy gradient
- actor critic
- parametric optimization
- reinforcement learning
- gradient method
- reinforcement learning algorithms
- function approximation
- optimal control
- approximation methods
- variance reduction
- model free reinforcement learning
- bayesian networks
- markov decision processes
- optimization methods
- single agent
- state action