dementrock
Re:RL²: Fast Reinforcement Learning via Slow Reinforcement Learning (2...
on Friday January 20, 2017 @12:58AM (#13441952)
(Author here)
This is a great question! There are at least two scenarios where having a meta-learning setup could help. The first is to learn the fast RL algorithm in simulation, by having a distribution over real world environments (varying physics, textures, etc), and then run it in the real world. The second is to learn a fast RL algorithm over a wide range of tasks (for example, on a set of training games in Universe), and (hopefully) generalize to unseen games, analogous to generalization in supervised learning.
Re:TensorFuse – Common interface for Theano, CGT, and TensorFlow
on Saturday February 20, 2016 @02:06PM (#11141398)
Actually TensorFuse does support RNN by porting a subset of scan to TensorFlow. I've been using it to port Lasagne to support TensorFlow: https://github.com/dementrock/Lasagne-tf. The examples/recurrent.py there actually works.
Good suggestion on Neon!
TensorFuse – Common interface for Theano, CGT, and TensorFlow
Supernormal Stimuli: The Seduction of Our Senses
Re:Fuse – Write cross platform native apps using C# and JavaScript
on Monday July 13, 2015 @10:27AM (#9878238)
OP here - I don't work for Fuse and I've got a related question. Will the Fuse libraries be open-sourced too?