Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revision Both sides next revision
hierarchical_abstraction [2018/02/25 11:59]
admin
hierarchical_abstraction [2018/10/08 21:26]
admin
Line 472: Line 472:
 https://​arxiv.org/​abs/​1712.00409 Deep Learning Scaling is Predictable,​ Empirically https://​arxiv.org/​abs/​1712.00409 Deep Learning Scaling is Predictable,​ Empirically
  
 +https://​arxiv.org/​pdf/​1804.02808v1.pdf Latent Space Policies for Hierarchical Reinforcement Learning
 +
 +First, each layer in the
 +hierarchy can be trained with exactly the same algorithm.
 +Second, by using an invertible mapping from latent variables
 +to actions, each layer becomes invertible, which means that
 +the higher layer can always perfectly invert any behavior of
 +the lower layer. This makes it possible to train lower layers
 +on heuristic shaping rewards, while higher layers can still
 +optimize task-specific rewards with good asymptotic performance.
 +Finally, our method has a natural interpretation
 +as an iterative procedure for constructing graphical models
 +that gradually simplify the task dynamics.
 +
 +https://​openreview.net/​forum?​id=S1JHhv6TW Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions ​
 +
 +We focus on dilated convolutional networks, a family of deep models delivering state of the art performance in sequence processing tasks. By introducing and analyzing the concept of mixed tensor decompositions,​ we prove that interconnecting dilated convolutional networks can lead to expressive efficiency. In particular, we show that even a single connection between intermediate layers can already lead to an almost quadratic gap, which in large-scale settings typically makes the difference between a model that is practical and one that is not
 +
 +https://​arxiv.org/​abs/​1807.04640v1 Automatically Composing Representation Transformations as a Means for Generalization
 +
 +https://​arxiv.org/​abs/​1807.07560v1 Compositional GAN: Learning Conditional Image Composition
 +
 +https://​arxiv.org/​pdf/​1803.00590.pdf Hierarchical Imitation and Reinforcement Learning
 +
 +We propose an algorithmic framework, called hierarchical
 +guidance, that leverages the hierarchical
 +structure of the underlying problem to integrate
 +different modes of expert interaction. Our
 +framework can incorporate different combinations
 +of imitation learning (IL) and reinforcement
 +learning (RL) at different levels, leading to dramatic
 +reductions in both expert effort and cost of
 +exploration.