Deep Reinforcement Learning Graphs: Feedback Motion Planning via Neural Lyapunov Verification.
Armin GhanbarzadehEsmaeil NajafiPublished in: CoRR (2023)
Keyphrases
- motion planning
- reinforcement learning
- control law
- degrees of freedom
- path planning
- mobile robot
- trajectory planning
- humanoid robot
- robot arm
- fitted q iteration
- adaptive control
- sensory inputs
- robotic tasks
- autonomous mobile robot
- multi robot
- nonlinear systems
- obstacle avoidance
- neural network
- markov decision processes
- model checking
- mechanical systems
- configuration space
- belief space
- robotic arm
- control scheme
- optimal policy
- collision free
- real robot
- inverse kinematics
- state space
- nonlinear dynamics
- model free
- sufficient conditions
- dynamic programming
- learning algorithm
- closed loop
- dynamical systems
- optimal control
- spatio temporal
- video sequences
- real time
- visual servoing
- robot control
- dynamic environments
- pose estimation
- biologically inspired