Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems.
Andreas SchlaginhaufenPhilippe WenkAndreas KrauseFlorian DörflerPublished in: CoRR (2021)
Keyphrases
- dynamical systems
- predictive state representations
- partially observed
- dynamic systems
- partially observable
- dynamical models
- prior knowledge
- reinforcement learning methods
- latent variable models
- dynamical behavior
- connectionist networks
- learning algorithm
- phase space
- statistical models
- state space
- agent environment
- nonlinear dynamical systems
- probabilistic model
- model free
- action selection
- stochastic model
- differential equations
- learning tasks
- model selection
- supervised learning