Evaluating the Robustness of Collaborative Agents
(2021)
Conference Proceeding
Knott, P., Carroll, M., Devlin, S., Ciosek, K., Hofmann, K., Dragan, A., & Shah, R. (2021). Evaluating the Robustness of Collaborative Agents. In AAMAS '21: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (1560-1562)
Artificial agents trained by deep reinforcement learning will likely encounter novel situations after deployment that were never seen during training. Our agent must be robust to handle such situations well. However, if we cannot rely on the average... Read More about Evaluating the Robustness of Collaborative Agents.