Wed Oct 26 2022
Tue Oct 25 2022
In-context Reinforcement Learning with Algorithm Distillation
Artificial Intelligence
Reinforcement Learning
Optimizing business processes through RL algorithms
Proposes Algorithm Distillation, a method for distilling RL algorithms into neural networks by modeling their training histories with a causal sequence model.
Can be used to create more data-efficient RL algorithms in a variety of environments with sparse rewards, combinatorial task structure, and pixel-based observations.
Redistributor: Learning to Transform Probability Distributions
Artificial Intelligence
Image Processing
Machine Learning
Optimizing data distribution in machine learning
Presents Redistributor, an algorithm and package that forces a collection of scalar samples to follow a desired distribution.
Can be used as a preprocessing step in machine learning and for various interesting use cases in image processing, such as producing visually appealing results.
Mon Oct 24 2022
Thu Oct 20 2022
Wed Oct 19 2022
Mon Oct 17 2022