Automatic Curriculum Learning with Gradient Reward Signals

no code implementations • 21 Dec 2023 • Ryan Campbell, Junsang Yoon

This paper investigates the impact of using gradient norm reward signals in the context of Automatic Curriculum Learning (ACL) for deep reinforcement learning (DRL).

reinforcement-learning

Can Transformers Learn Sequential Function Classes In Context?

1 code implementation • 19 Dec 2023 • Ryan Campbell, Emma Guo, Evan Hu, Reya Vir, Ethan Hsiao

We provide evidence that transformers can reason with and understand sequentiality encoded within function classes, as reflected by the effective learning of our proposed tasks.

In-Context Learning

Adversarial Boot Camp: label free certified robustness in one epoch

1 code implementation • 5 Oct 2020 • Ryan Campbell, Chris Finlay, Adam M Oberman

Machine learning models are vulnerable to adversarial attacks.

Deterministic Gaussian Averaged Neural Networks

1 code implementation • 10 Jun 2020 • Ryan Campbell, Chris Finlay, Adam M. Oberman

We present a deterministic method to compute the Gaussian average of neural networks used in regression and classification.

Adversarial Robustness regression