Safe Locomotion Within Confined Workspace using Deep Reinforcement Learning.
Apan DastiderSayyed Jaffar Ali RazaMingjie LinPublished in: IRC (2021)
Keyphrases
- reinforcement learning
- robot control
- function approximation
- reinforcement learning algorithms
- mobile robot
- state space
- degrees of freedom
- autonomous learning
- learning algorithm
- optimal policy
- model free
- direct policy search
- deep learning
- multi agent
- machine learning
- action selection
- function approximators
- stochastic approximation
- data sets
- policy search
- parallel robot
- database