Corpus ID: 220646813

Structure Mapping for Transferability of Causal Models

@article{Pruthi2020StructureMF,
  title={Structure Mapping for Transferability of Causal Models},
  author={Purva Pruthi and Javier Gonz'alez and Xiaoyu Lu and Madalina Fiterau},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.09445}
}
Human beings learn causal models and constantly use them to transfer knowledge between similar environments. We use this intuition to design a transfer-learning framework using object-oriented representations to learn the causal relationships between objects. A learned causal dynamics model can be used to transfer between variants of an environment with exchangeable perceptual features among objects but with the same underlying causal dynamics. We adapt continuous optimization for structure… Expand
On the Convergence of Continuous Constrained Optimization for Structure Learning
TLDR
This work reviews the standard convergence result of the ALM and shows that the required conditions are not satisfied in the recent continuous constrained formulation for learning DAGs, and establishes the convergence guarantee of QPM to a DAG solution, under mild conditions, based on a property of the DAG constraint term. Expand

References

SHOWING 1-10 OF 13 REFERENCES
Learning to Learn Causal Models
TLDR
A hierarchical Bayesian framework is presented that helps to explain how learning about several causal systems can accelerate learning about systems that are subsequently encountered and confirms that humans learn rapidly about the causal powers of novel objects. Expand
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
TLDR
The Schema Network is introduced, an object-oriented generative physics simulator capable of disentangling multiple causes of events and reasoning backward through causes to achieve goals, and generalizing from limited data and learning causal relationships are essential abilities on the path toward generally intelligent systems. Expand
An object-oriented representation for efficient reinforcement learning
TLDR
Object-Oriented MDPs (OO-MDPs) are introduced, a representation based on objects and their interactions, which is a natural way of modeling environments and offers important generalization opportunities and a polynomial bound on its sample complexity is proved. Expand
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
TLDR
It is demonstrated that neural network dynamics models can in fact be combined with model predictive control (MPC) to achieve excellent sample complexity in a model-based reinforcement learning algorithm, producing stable and plausible gaits that accomplish various complex locomotion tasks. Expand
Categorization as causal reasoning
  • B. Rehder
  • Psychology, Computer Science
  • Cogn. Sci.
  • 2003
TLDR
Quantitative fits of causal-model theory were superior to those obtained with extensions to traditional similarity-based models that represent causal knowledge either as higher-order relational features or “prior exemplars” stored in memory. Expand
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural networkExpand
Learning Sparse Nonparametric DAGs
TLDR
A completely general framework for learning sparse nonparametric directed acyclic graphs (DAGs) from data is developed that can be applied to general nonlinear models, general differentiable loss functions, and generic black-box optimization routines. Expand
DAGs with NO TEARS: Continuous Optimization for Structure Learning
TLDR
This paper forms the structure learning problem as a purely continuous optimization problem over real matrices that avoids this combinatorial constraint entirely and achieves a novel characterization of acyclicity that is not only smooth but also exact. Expand
Goals and Habits in the Brain
TLDR
This work reviews four generations of work in this tradition of experimental work in cognitive neuroscience and provides pointers to the forefront of the field’s fifth generation. Expand
Self-Attentional Credit Assignment for Transfer in Reinforcement Learning
TLDR
SECRET is a novel approach to transfer learning for RL that uses a backward-view credit assignment mechanism based on a self-attentive architecture and can be supplemented by transfer methods that do not modify the reward function and it can be plugged on top of any RL algorithm. Expand
...
1
2
...