Generative Adversarial Simulator

by   Jonathan Raiman, et al.

Knowledge distillation between machine learning models has opened many new avenues for parameter count reduction, performance improvements, or amortizing training time when changing architectures between the teacher and student network. In the case of reinforcement learning, this technique has also been applied to distill teacher policies to students. Until now, policy distillation required access to a simulator or real world trajectories. In this paper we introduce a simulator-free approach to knowledge distillation in the context of reinforcement learning. A key challenge is having the student learn the multiplicity of cases that correspond to a given action. While prior work has shown that data-free knowledge distillation is possible with supervised learning models by generating synthetic examples, these approaches to are vulnerable to only producing a single prototype example for each class. We propose an extension to explicitly handle multiple observations per output class that seeks to find as many exemplars as possible for a given output class by reinitializing our data generator and making use of an adversarial loss. To the best of our knowledge, this is the first demonstration of simulator-free knowledge distillation between a teacher and a student policy. This new approach improves over the state of the art on data-free learning of student networks on benchmark datasets (MNIST, Fashion-MNIST, CIFAR-10), and we also demonstrate that it specifically tackles issues with multiple input modes. We also identify open problems when distilling agents trained in high dimensional environments such as Pong, Breakout, or Seaquest.


Learning the Wrong Lessons: Inserting Trojans During Knowledge Distillation

In recent years, knowledge distillation has become a cornerstone of effi...

Learning from a Lightweight Teacher for Efficient Knowledge Distillation

Knowledge Distillation (KD) is an effective framework for compressing de...

Relational Knowledge Distillation

Knowledge distillation aims at transferring knowledge acquired in one mo...

Student-friendly Knowledge Distillation

In knowledge distillation, the knowledge from the teacher model is often...

Robustness and Diversity Seeking Data-Free Knowledge Distillation

Knowledge distillation (KD) has enabled remarkable progress in model com...

Undistillable: Making A Nasty Teacher That CANNOT teach students

Knowledge Distillation (KD) is a widely used technique to transfer knowl...

Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation

Knowledge distillation refers to a technique of transferring the knowled...

Please sign up or login with your details

Forgot password? Click here to reset