PEARL: PrEference Appraisal Reinforcement Learning for Motion Planning.
Aleksandra FaustHao-Tien Lewis ChiangLydia TapiaPublished in: CoRR (2018)
Keyphrases
- motion planning
- reinforcement learning
- degrees of freedom
- mobile robot
- trajectory planning
- path planning
- robot arm
- humanoid robot
- robotic tasks
- autonomous mobile robot
- model free
- state space
- robotic arm
- multi robot
- markov decision processes
- configuration space
- robot control
- obstacle avoidance
- belief space
- learning algorithm
- causal models
- optimal policy
- multi agent
- real robot
- inverse kinematics
- real time
- belief revision
- dynamic programming
- image sequences
- three dimensional
- nearest neighbor searching