Popular repositories Loading

1. Intuitor Intuitor Public

   Code for the paper: "Learning to Reason without External Rewards"

   Python 357 41

2. rl-generalization rl-generalization Public

   Modifiable OpenAI Gym environments for studying generalization in RL

   Python 87 14

3. cybergym cybergym Public

   CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

   Python 72 13

4. dpml-benchmark dpml-benchmark Public

   This repository contains the codes for first large-scale investigation of Differentially Private Convex Optimization algorithms.

   Python 63 18

5. blackbox-attacks blackbox-attacks Public

   Code used in 'Exploring the Space of Black-box Attacks on Deep Neural Networks' (https://arxiv.org/abs/1712.09491)

   Python 61 13

6. Virgo Virgo Public

   C++ 59 17