behzadanksu / rl-attack
Adversarial Example Attacks on Policy Learners
☆39Updated 4 years ago
Related projects: ⓘ
- ☆26Updated last year
- Code for "Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight"☆78Updated 6 years ago
- Code used in our paper "Robust Deep Reinforment Learning through Adversarial Loss"☆32Updated 11 months ago
- Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework☆58Updated 3 years ago
- [NeurIPS 2020, Spotlight] Code for "Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations"☆110Updated 2 years ago
- Learning Backtracking Models, ICLR'19☆10Updated 6 years ago
- Efficient Robustness Verification for ReLU networks (this repository is outdated, don't use; checkout our new implementation at https://g…☆30Updated 4 years ago
- Code to train RL agents along with Adversarial distrubance agents☆63Updated 7 years ago
- ☆26Updated 3 years ago
- Adversarial attacks on Deep Reinforcement Learning (RL)☆76Updated 3 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆40Updated 5 years ago
- Code for human intervention reinforcement learning☆33Updated 6 years ago
- ☆26Updated last year
- [NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning☆31Updated 3 years ago
- Replication Package for "Mind Your Data! Hiding Backdoors in Offline Reinforcement Learning Datasets", IEEE S&P 2024.☆21Updated last month
- Code for the CoRL 2019 paper AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers☆24Updated last year
- Pytorch implementation of LOLA (https://arxiv.org/abs/1709.04326) using DiCE (https://arxiv.org/abs/1802.05098)☆90Updated 6 years ago
- Safe Reinforcement Learning algorithms☆69Updated 2 years ago
- Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning / ICLR 2020☆53Updated 4 years ago
- Open source implementation of the TrojDRL algorithm presented in TrojDRL: Evaluation of backdoor attacks on Deep Reinforcement Learning☆14Updated 4 years ago
- Simple grid-world environment compatible with OpenAI-gym☆49Updated 4 years ago
- ☆12Updated last year
- Code implementation of: "Graying the black box: Understanding DQNs"☆19Updated 7 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- Pytorch implementation of "FeUdal Networks for Hierarchical Reinforcement Learning" for Montezuma's Revenge☆92Updated 2 years ago
- General-purpose library for extracting interpretable models from Multi-Agent Reinforcement Learning systems☆19Updated 4 years ago
- ☆26Updated 5 years ago
- Gym environments modified with adversarial agents☆35Updated 7 years ago
- A Multi-agent Learning Framework☆61Updated 3 years ago
- ☆32Updated 6 years ago