alan-turing-institute / cage-challenge-2-public
Team Mindrake's hierarchical RL solution to the second CybORG CAGE challenge.
☆9Updated last year
Related projects: ⓘ
- TTCP CAGE Challenge 2☆46Updated 3 months ago
- The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. Thi…☆34Updated last month
- Cyber Operations Research Gym☆59Updated 3 months ago
- Adversarial attacks on Deep Reinforcement Learning (RL)☆76Updated 3 years ago
- ☆50Updated last year
- An Abstract Cyber Security Simulation and Markov Game for OpenAI Gym☆70Updated last year
- ☆18Updated 2 years ago
- Multi-Agent Reinforcement Learning on network-security☆16Updated 2 years ago
- Code for "Convergence of Learning Dynamics in Stackelberg Games"☆13Updated 4 years ago
- Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework☆58Updated 3 years ago
- TTCP CAGE Challenge 3☆34Updated 5 months ago
- [NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning☆31Updated 3 years ago
- Gym-based environment for training offensive RL agents. Agents can generalize to unseen scenarios and simulation-trained agents can be de…☆31Updated 2 months ago
- Adversarial attacks in consensus-based multi-agent reinforcement learning☆16Updated last year
- [NeurIPS 2020, Spotlight] Code for "Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations"☆110Updated 2 years ago
- An open, minimalist Gymnasium environment for autonomous coordination in wireless mobile networks.☆97Updated 5 months ago
- Replication Package for "Mind Your Data! Hiding Backdoors in Offline Reinforcement Learning Datasets", IEEE S&P 2024.☆21Updated last month
- ☆26Updated last year
- ☆10Updated last year
- ☆12Updated last year
- A Simulated Optimal Intrusion Response Game☆19Updated 2 years ago
- NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms☆321Updated 6 months ago
- PenGym: Pentesting Training Framework for Reinforcement Learning Agents☆20Updated last month
- Level-Based Foraging (LBF): A multi-agent reinforcement learning environment☆38Updated this week
- ☆11Updated 4 years ago
- Adversarial Reinforcement Learning papers (single-agent setting and multi-agent setting)☆53Updated 2 years ago
- Open source implementation of the TrojDRL algorithm presented in TrojDRL: Evaluation of backdoor attacks on Deep Reinforcement Learning☆14Updated 4 years ago
- ARCD Primary-Level AI Training Environment (PrimAITE)☆17Updated 9 months ago
- Adversarial Example Attacks on Policy Learners☆39Updated 4 years ago
- ☆197Updated 7 months ago