Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding.
Peter HeBorja G. LeónFrancesco BelardinelliPublished in: SafeAI@AAAI (2022)
Keyphrases
- reinforcement learning
- latent variables
- function approximation
- fuel consumption
- model free
- multi agent
- robotic control
- state space
- optimal policy
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- random variables
- neural network
- learning classifier systems
- supervised learning
- probabilistic model
- traffic accidents
- temporal difference learning
- learning process
- machine learning