Failure Prevention in Bimanual Robots using Deep Deterministic Policy Gradient.
Asel MenekseAbdullah Cihan AkSanem SarielPublished in: SIU (2024)
Keyphrases
- policy gradient
- humanoid robot
- actor critic
- reinforcement learning
- mobile robot
- parametric optimization
- function approximation
- gradient method
- optimal control
- reinforcement learning algorithms
- model free reinforcement learning
- reinforcement learning methods
- cooperative
- approximation methods
- robotic systems
- partially observable markov decision processes
- function approximators
- convergence rate
- domain independent
- supervised learning