Assume-Guarantee Reinforcement Learning.
Milad KazemiMateo PerezFabio SomenziSadegh SoudjaniAshutosh TrivediAlvaro VelasquezPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- learning algorithm
- optimal policy
- reinforcement learning algorithms
- direct policy search
- reinforcement learning methods
- control problems
- multi agent
- machine learning
- temporal difference
- learning problems
- robotic control
- multiscale
- optimal control
- action selection
- learning process
- markov decision process
- markov decision processes
- independent and identically distributed
- stochastic approximation
- transition model