Verified Probabilistic Policies for Deep Reinforcement Learning.
Edoardo BacciDavid ParkerPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- reward function
- control policies
- reinforcement learning algorithms
- data driven
- generative model
- state space
- probabilistic logic
- model free
- reinforcement learning agents
- policy gradient methods
- uncertain data
- function approximation
- fitted q iteration
- machine learning
- markov decision problems
- management policies
- hierarchical reinforcement learning
- robotic control
- partially observable markov decision processes
- markov decision processes
- transfer learning
- probabilistic model
- bayesian networks
- deep learning
- control policy
- learning classifier systems
- belief networks
- decision problems
- learning algorithm