Search Results for author:
Found 2 papers, 1 papers with code
Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning
Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios.
Regret-Based Defense in Adversarial Reinforcement Learning
We demonstrate that our approaches provide a significant improvement in performance across a wide variety of benchmarks against leading approaches for robust Deep RL.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
