Sumitra Ganesh

Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems

2022 · arXiv (Cornell University)

Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world application where noise and potential attackers exist, …

Approximate Equivariance in Reinforcement Learning

2024 · arXiv (Cornell University)

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is present, which makes imposing exact …