Roman Belaire

According to our database, Roman Belaire authored at least 5 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Automatic LLM Red Teaming.

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

CoRR, August, 2025

On Minimizing Adversarial Counterfactual Error in Adversarial Reinforcement Learning.

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning.

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

CoRR, 2024

Regret-based Defense in Adversarial Reinforcement Learning.

Roman Belaire, Pradeep Varakantham, Thanh Hong Nguyen, David Lo

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

2023

Regret-Based Optimization for Robust Reinforcement Learning.

Roman Belaire, Pradeep Varakantham, David Lo

CoRR, 2023