Probabilistic Counterexample Guidance for Safer Reinforcement Learning.
Xiaotong JiAntonio FilieriPublished in: QEST (2023)
Keyphrases
- reinforcement learning
- bayesian networks
- generative model
- probabilistic model
- learning algorithm
- multi agent
- reinforcement learning algorithms
- temporal difference
- dynamic programming
- markov decision processes
- data sets
- function approximation
- uncertain data
- optimal policy
- state space
- machine learning
- database
- model checking
- semi supervised
- learning classifier systems
- probabilistic logic
- robot control
- markov decision process