Path Planning for Multi-Arm Manipulators Using Deep Reinforcement Learning: Soft Actor-Critic with Hindsight Experience Replay.
Evan PriantoMyeongseop KimJae-Han ParkJi-Hun BaeJung-Su KimPublished in: Sensors (2020)
Keyphrases
- path planning
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- approximate dynamic programming
- reinforcement learning algorithms
- optimal control
- mobile robot
- gradient method
- path planning algorithm
- dynamic environments
- neuro fuzzy
- function approximation
- multi robot
- motion planning
- policy iteration
- model free
- markov decision processes
- action selection
- optimal path
- average reward
- machine learning
- optimal policy
- decision problems
- path finding
- temporal difference learning
- multiple robots
- step size
- dynamic programming
- convergence rate
- long run
- control law
- degrees of freedom
- reinforcement learning methods
- rl algorithms
- robotic systems
- evaluation function