Reinforcement Learning based Carbon Nanotube Growth Automation.
Ashish PandeyRamakrishna SuryaMatthew R. MaschmannPrasad CalyamPublished in: AIPR (2021)
Keyphrases
- reinforcement learning
- carbon nanotubes
- function approximation
- state space
- learning algorithm
- model free
- multi agent
- learning process
- reinforcement learning algorithms
- temporal difference
- learning capabilities
- optimal policy
- action selection
- markov decision processes
- temporal difference learning
- optimal control
- learning classifier systems
- growth rate
- learning agents
- autonomous learning
- transition model
- growth model
- robotic control
- direct policy search
- robot control
- real robot
- machine learning
- radial basis function
- transfer learning
- supervised learning
- mobile robot
- search space
- artificial intelligence
- information retrieval