DeepAI AI Chat
Log In Sign Up

Cascade Attribute Learning Network

by   Zhuo Xu, et al.
Tsinghua University
berkeley college

We propose the cascade attribute learning network (CALNet), which can learn attributes in a control task separately and assemble them together. Our contribution is twofold: first we propose attribute learning in reinforcement learning (RL). Attributes used to be modeled using constraint functions or terms in the objective function, making it hard to transfer. Attribute learning, on the other hand, models these task properties as modules in the policy network. We also propose using novel cascading compensative networks in the CALNet to learn and assemble attributes. Using the CALNet, one can zero shoot an unseen task by separately learning all its attributes, and assembling the attribute modules. We have validated the capacity of our model on a wide variety of control problems with attributes in time, position, velocity and acceleration phases.


page 1

page 4

page 5


Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks

Reinforcement learning methods have been developed to achieve great succ...

A Deep Cascade Network for Unaligned Face Attribute Classification

Humans focus attention on different face regions when recognizing face a...

Multiplicative Coevolution Regression Models for Longitudinal Networks and Nodal Attributes

We introduce a simple and extendable coevolution model for the analysis ...

Planning Multimodal Exploratory Actions for Online Robot Attribute Learning

Robots frequently need to perceive object attributes, such as "red," "he...

Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks

Learning to transfer visual attributes requires supervision dataset. Cor...

Constructing High Precision Knowledge Bases with Subjective and Factual Attributes

Knowledge bases (KBs) are the backbone of many ubiquitous applications a...

Variation Network: Learning High-level Attributes for Controlled Input Manipulation

This paper presents the Variation Network (VarNet), a generative model p...