Model-Based Reinforcement Learning via Stochastic Hybrid Models
–arXiv.org Artificial Intelligence
Optimal control of general nonlinear systems is a central challenge in automation. Enabled by powerful function approximators, data-driven approaches to control have recently successfully tackled challenging applications. However, such methods often obscure the structure of dynamics and control behind black-box over-parameterized representations, thus limiting our ability to understand closed-loop behavior. This paper adopts a hybrid-system view of nonlinear modeling and control that lends an explicit hierarchical structure to the problem and breaks down complex dynamics into simpler localized units. We consider a sequence modeling paradigm that captures the temporal structure of the data and derive an expectation-maximization (EM) algorithm that automatically decomposes nonlinear dynamics into stochastic piecewise affine models with nonlinear transition boundaries. Furthermore, we show that these time-series models naturally admit a closed-loop extension that we use to extract local polynomial feedback controllers from nonlinear experts via behavioral cloning. Finally, we introduce a novel hybrid relative entropy policy search (Hb-REPS) technique that incorporates the hierarchical nature of hybrid models and optimizes a set of time-invariant piecewise feedback controllers derived from a piecewise polynomial approximation of a global state-value function.
arXiv.org Artificial Intelligence
Jun-20-2023
- Country:
- North America > United States
- Massachusetts > Hampshire County
- Amherst (0.04)
- California > Alameda County
- Berkeley (0.04)
- Massachusetts > Hampshire County
- Europe
- Finland (0.04)
- Germany > Hesse
- Darmstadt Region > Darmstadt (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Overview (0.46)
- Research Report (0.40)
- Technology:
- Information Technology > Artificial Intelligence
- Representation & Reasoning
- Uncertainty > Bayesian Inference (1.00)
- Optimization (1.00)
- Machine Learning
- Statistical Learning (1.00)
- Reinforcement Learning (1.00)
- Neural Networks (1.00)
- Learning Graphical Models
- Directed Networks > Bayesian Learning (1.00)
- Undirected Networks > Markov Models (0.69)
- Representation & Reasoning
- Information Technology > Artificial Intelligence