Towards Real-World Force-Sensitive Robotic Assembly through Deep Reinforcement Learning in Simulations.
Marius HebeckerJens LambrechtMarkus SchmitzPublished in: AIM (2021)
Keyphrases
- real world
- reinforcement learning
- real robot
- robotic manipulator
- real time
- robotic systems
- learning algorithm
- wide range
- robotic tasks
- data sets
- data mining
- state space
- mobile robot
- optimal policy
- numerical simulations
- function approximation
- robotic control
- perception action
- markov decision processes
- neural network
- reinforcement learning algorithms
- model free
- multi agent reinforcement learning
- position control
- synthetic data
- learning process
- tactile sensing