Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning.
Zikang XiongSuresh JagannathanPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- program synthesis
- model free
- partially observable
- controller synthesis
- optimal policy
- deep learning
- temporal difference learning
- evolutionary algorithm
- machine learning
- supervised learning
- transfer learning
- learning classifier systems
- learning process
- policy gradient
- multi agent reinforcement learning
- transition model
- autonomous learning
- robotic control
- control policies
- data sets
- behavioural cloning
- function approximators
- memory efficient
- reinforcement learning algorithms
- temporal difference
- texture synthesis
- learning problems
- lightweight
- least squares
- dynamic programming
- multi agent
- neural network