RESPRECT: Speeding-up Multi-fingered Grasping with Residual Reinforcement Learning.
Federico CeolaLorenzo RosascoLorenzo NatalePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- object manipulation
- control theoretic
- robot control
- function approximation
- multi agent
- temporal difference
- learning process
- human robot interaction
- model free
- autonomous learning
- state space
- vision system
- dynamic environments
- machine learning
- biologically inspired
- reinforcement learning algorithms
- control architecture
- decision trees
- learning algorithm
- genetic algorithm