How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation.
Alex X. LeeColine DevinJost Tobias SpringenbergYuxiang ZhouThomas LampeAbbas AbdolmalekiKonstantinos BousmalisPublished in: IROS (2022)
Keyphrases
- manipulation tasks
- reinforcement learning
- real robot
- parallel robot
- mobile robot
- robotic systems
- real time
- robot navigation
- vision system
- human robot interaction
- robotic arm
- robot control
- object manipulation
- robotic control
- humanoid robot
- augmented reality
- visual landmarks
- service robots
- imitation learning
- motion planning
- multi robot
- visual servoing
- function approximation
- hand eye
- autonomous robots
- end effector
- tactile sensing
- markov decision processes
- human computer interaction
- semi autonomous
- learning algorithm
- computer vision
- dynamic programming
- state space
- robotic platform
- robot behavior
- inverse kinematics
- dynamic environments
- perception action
- robot arm
- robot programming
- unstructured environments
- position and orientation
- autonomous learning
- reinforcement learning algorithms