From POMDP Executions to Probabilistic Axioms.
Daniele MeliGiulio MazziAlberto CastelliniAlessandro FarinelliPublished in: OVERLAY@AI*IA (2022)
Keyphrases
- reinforcement learning
- knowledge base
- dynamical systems
- planning under uncertainty
- state space
- partially observable markov decision processes
- bayesian networks
- probabilistic model
- generative model
- first order logic
- uncertain data
- partially observable markov decision process
- neural network
- probabilistic planning
- posterior probability
- optimal policy
- search algorithm
- multi agent
- machine learning