Formal Policy Synthesis for Continuous-State Systems via Reinforcement Learning.
Milad KazemiSadegh SoudjaniPublished in: IFM (2020)
Keyphrases
- continuous state
- reinforcement learning
- policy search
- control policies
- action space
- state dependent
- optimal policy
- robot navigation
- partially observable markov decision processes
- state space
- continuous state spaces
- action selection
- machine learning
- control system
- markov decision processes
- state action
- continuous action
- continuous state and action spaces
- reinforcement learning algorithms
- planning problems
- dynamic programming
- multi agent