Propagation Networks for Model-Based Control Under Partial Observation
Explore this paper's citation graph
- Type
- preprint
- Published
- 2018-09-28
- Cited by
- 158
- References
- 36
- Access
- Open access
- OpenAlex
- https://openalex.org/W2893271281
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52894291
Keywords
Observable, Computer science, Pairwise comparison, Reinforcement learning, Differentiable function
References
- Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching
- MuJoCo: A physics engine for model-based control
- Rigid-Body Dynamics with Friction and Impact
- Deep Residual Learning for Image Recognition
- DeepMPC: Learning Deep Latent Features for Model Predictive Control
- PID Controllers: Theory, Design, and Tuning
- A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS
- Underactuated Robotics: Learning, Planning, and Control for Ecient and Agile Machines Course Notes for MIT 6.832
- The Predictron: End-To-End Learning and Planning
- Neural Message Passing for Quantum Chemistry
- Proximal Policy Optimization Algorithms
- Imagination-Augmented Agents for Deep Reinforcement Learning
- Learning model-based planning from scratch
- Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
- Fundamental Limitations in Performance and Interpretability of Common Planar Rigid-Body Contact Models
- Universal Planning Networks
- Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning
- Simple Recurrent Units for Highly Parallelizable Recurrence
- End-to-End Differentiable Physics for Learning and Control
- Experimental Validation of Contact Dynamics for In-Hand Manipulation
Cited by
- Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects
- Learning Compositional Koopman Operators for Model-Based Control
- Predicting the Physical Dynamics of Unseen 3D Objects
- Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects
- Learning to Simulate Complex Physics with Graph Networks
- Belief Regulated Dual Propagation Nets for Learning Action Effects on Groups of Articulated Objects
- Accurately Solving Physical Systems with Graph Learning
- Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
- Visual Grounding of Learned Physical Models
- Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction
- Learning Long-term Visual Dynamics with Region Proposal Interaction Networks
- Learning Topological Motion Primitives for Knot Planning
- Learning to Abstract and Compose Mechanical Device Function and Behavior
- Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
- Differentiable Predictive Control: An MPC Alternative for Unknown Nonlinear Systems using Constrained Deep Learning
- An End-to-End Differentiable but Explainable Physics Engine for Tensegrity Robots: Modeling and Control
- Spring-Rod System Identification via Differentiable Physics Engine
- Learning Physical Constraints with Neural Projections
- SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
- Causal Discovery in Physical Systems from Videos
Related papers
- CALCULATION OF EXPECTED VALUES OF OBSERVABLES IN SOME PROBLEMS OF STATISTICAL GEOMORPHOLOGY
- The validity of pairwise models in predicting community dynamics
- Continuous Differentiability in the Context of Generalized Approach to Differentiability
- The Role of Observables and Non-observables in Chemistry: A Critique of Chemical Language
- Non-pairwise Collaborative Filtering
- Estimating the expectation values of spin-1/2 observables with finite resources