Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates.
Shixiang GuEthan HollyTimothy P. LillicrapSergey LevinePublished in: ICRA (2017)
Keyphrases
- reinforcement learning
- manipulation tasks
- real robot
- mobile robot
- perception action
- function approximation
- imitation learning
- robotic systems
- state space
- robot control
- optimal policy
- real time
- database
- markov decision processes
- robotic control
- object manipulation
- human robot interaction
- model free
- robot navigation
- reinforcement learning algorithms
- data sets
- multi agent
- asynchronous communication
- temporal difference learning
- action space
- learning algorithm
- robotic arm
- reinforcement learning methods
- function approximators
- learning process
- dynamic programming
- supervised learning
- learning problems