Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
Chace Ashcraft, Ted Staley, Josh Carney +4
Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet da…
cs.LG2024
IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
Vindula Jayawardana, Baptiste Freydt, Ao Qu +3
Despite the popularity of multi-agent reinforcement learning (RL) in simulated and two-player applications, its success in messy real-world applications has been limited. A key cha…