STL-Based Synthesis of Feedback Controllers Using Reinforcement Learning.
Nikhil Kumar SinghIndranil SahaPublished in: AAAI (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- state space
- controller synthesis
- multi agent
- markov decision processes
- transfer learning
- optimal control
- temporal difference
- user feedback
- feedback mechanisms
- machine learning
- temporal difference learning
- reinforcement learning methods
- neural network
- functional programs
- motor skills
- control policies
- sensory inputs
- control policy
- markov decision process
- texture synthesis
- learning process
- learning problems