Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation
arXiv:2005.01432
Abstract
The control of nonlinear dynamical systems remains a major challenge for autonomous agents. Current trends in reinforcement learning (RL) focus on complex representations of dynamics and policies, which have yielded impressive results in solving a variety of hard control tasks. However, this new sophistication and extremely over-parameterized models have come with the cost of an overall reduction in our ability to interpret the resulting policies. In this paper, we take inspiration from the control community and apply the principles of hybrid switching systems in order to break down complex dynamics into simpler components. We exploit the rich representational power of probabilistic graphical models and derive an expectation-maximization (EM) algorithm for learning a sequence model to capture the temporal structure of the data and automatically decompose nonlinear dynamics into stochastic switching linear dynamical systems. Moreover, we show how this framework of switching models enables extracting hierarchies of Markovian and auto-regressive locally linear controllers from nonlinear experts in an imitation learning scenario.
arXiv comment2nd Annual Conference on Learning for Dynamics and Control
References in corpus (9)
- Continuous control with deep reinforcement learning
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Trust Region Policy Optimization
- On the Number of Linear Regions of Deep Neural Networks
- Understanding Deep Neural Networks with Rectified Linear Units
- Bounding and Counting Linear Regions of Deep Neural Networks
- Expressiveness of Rectifier Networks
- A Bayesian Approach to Policy Recognition and State Representation Learning
- Hybrid system identification using switching density networks