Causal Navigation by Continuous-time Neural Networks
arXiv:2106.08314
Abstract
Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to domain shifts by failing to account for the causal relationships between the agent and the environment. In this paper, we propose a theoretical and experimental framework for learning causal representations using continuous-time neural networks, specifically over their discrete-time counterparts. We evaluate our method in the context of visual-control learning of drones over a series of complex tasks, ranging from short- and long-term navigation, to chasing static and dynamic objects through photorealistic environments. Our results demonstrate that causal continuous-time deep models can perform robust navigation tasks, where advanced recurrent models fail. These models learn complex causal control representations directly from raw visual inputs and scale to solve a variety of tasks using imitation learning.
arXiv comment24 Pages
References in corpus (20)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- Learning to Explore using Active Neural SLAM
- Continuous Time Bayesian Networks
- Latent ODEs for Irregularly-Sampled Time Series
- Causality for Machine Learning
- ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
- Unifying Map and Landmark Based Representations for Visual Navigation
- Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
- One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
- VisualBackProp: efficient visualization of CNNs
- Learning to Control PDEs with Differentiable Physics
- From Ordinary Differential Equations to Structural Causal Models: the deterministic case
- Discrete Event, Continuous Time RNNs
- SNODE: Spectral Discretization of Neural ODEs for System Identification
- From Deterministic ODEs to Dynamic Structural Causal Models
- Adversarial Imitation Learning from Incomplete Demonstrations
- On The Verification of Neural ODEs with Stochastic Guarantees
- Sparse Flows: Pruning Continuous-depth Models
- GoTube: Scalable Stochastic Verification of Continuous-Depth Models