Be considerate: Avoiding negative side effects in reinforcement learning P Alizadeh Alamdari, TQ Klassen, R Toro Icarte, SA McIlraith Proceedings of the 21st International Conference on Autonomous Agents and …, 2022 | 24* | 2022 |
Formal methods with a touch of magic PA Alamdari, G Avni, TA Henzinger, A Lukina Proceedings of the 20th Conference on Formal Methods in Computer-Aided …, 2020 | 17 | 2020 |
Epistemic side effects: An AI safety problem TQ Klassen, PA Alamdari, SA McIlraith Proceedings of the 2023 International Conference on Autonomous Agents and …, 2023 | 4 | 2023 |
Avoiding Negative Side Effects by Considering Others PA Alamdari, TQ Klassen, RT Icarte, SA McIlraith NeurIPS SafeRL Workshop, 2021 | 4 | 2021 |
Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making PA Alamdari, TQ Klassen, E Creager, SA McIlraith Proceedings of the 41th International Conference on Machine Learning (ICML …, 2024 | 3* | 2024 |
Epistemic Side Effects & Avoiding Them (Sometimes) TQ Klassen, PA Alamdari, SA McIlraith NeurIPS ML Safety Workshop, 2022 | 2 | 2022 |
Policy Aggregation PA Alamdari, S Ebadian, AD Procaccia Advances in Neural Information Processing Systems (NeurIPS), 2024, 2024 | 1 | 2024 |
Poseidon Team Description Paper RoboCup 2013, Eindhoven A Afzal, P Alizadeh, MA Nezhad, K Ghaffari, G Hasanpour, K Jahedi, ... RoboCup, 2013 | 1 | 2013 |
Jump Starting Bandits with LLM-Generated Prior Knowledge PA Alamdari, Y Cao, KH Wilson The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024, 2024 | | 2024 |
Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI PA Alamdari, TQ Klassen, RT Icarte, SA McIlraith Pluralistic Alignment Workshop at NeurIPS 2024, 2024 | | 2024 |
Pluralistic Alignment Over Time TQ Klassen, PA Alamdari, SA McIlraith Pluralistic Alignment Workshop at NeurIPS 2024, 2024 | | 2024 |