Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning.
Abdullah AkgülManuel HaußmannMelih KandemirPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- model free
- partial observability
- function approximation
- reinforcement learning algorithms
- multi agent
- state space
- real time
- machine learning
- learning algorithm
- data driven
- optimal policy
- uncertain data
- optimal control
- temporal difference
- transition model
- artificial intelligence
- neural network
- data sets