- End-to-End Training of Deep Visuomotor Policies
- Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
- Deep Spatial Autoencoders for Visuomotor Learning
- Deep Kalman Filters
- Continuous Deep Q-Learning with Model-based Acceleration
- Deep Visual Foresight for Planning Robot Motion
- Interaction Networks for Learning about Objects, Relations and Physics
- A Compositional Object-Based Approach to Learning Physical Dynamics
- QMDP-Net: Deep Learning for Planning under Partial Observability
- Path Integral Networks: End-to-End Differentiable Optimal Control
- Data-driven discovery of Koopman eigen functions for control
- Learning model-based planning from scratch
- MBMF: Model-Based Priors for Model-Free Reinforcement Learning
- SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control
- Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition
- Robust Locally-Linear Controllable Embedding
- Efficient Model–Based Deep Reinforcement Learning with Variational State Tabulation
- Generative Temporal Models with Spatial Memory for Partially Observed Environments
- Deep Dynamical Modeling and Control of Unsteady Fluid Flows
- Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
- Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
- Graph Networks as Learnable Physics Engines for Inference and Control
- SPNets: Differentiable Fluid Dynamics for Deep Neural Networks
- Learning Plannable Representations with Causal InfoGAN
- Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
- SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning
- Recurrent World Models Facilitate Policy Evolution
- Propagation Networks for Model-Based Control Under Partial Observation
- Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
- Differentiable MPC for End-to-end Planning and Control
- Learning Latent Dynamics for Planning from Pixels
- Learning Physical Dynamical Systems for Prediction and Control: A Survey
- Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning
- Control-Limited Differential Dynamic Programming
- Unsupervised Learning for Physical Interaction through Video Prediction
- Deep learning for universal linear embeddings of nonlinear dynamics