Dextrous Tactile In-Hand Manipulation Using a Modular Reinforcement Learning Architecture.
Johannes PitzLennart RöstelLeon SieversBerthold BäumlPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- modular architecture
- autonomous learning
- machine learning
- software architecture
- markov decision processes
- function approximation
- highly modular
- learning capabilities
- temporal difference
- network architecture
- database
- human computer interaction
- model free
- management system
- reinforcement learning algorithms
- state space
- architectural design
- learning algorithm
- layered architecture
- neural network
- data sets