Export Citations
Publications
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- extended-abstract
Defining Deception in Decision Making
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems•May 2024, pp 2111-2113With the growing capabilities of machine learning systems, particularly those that communicate or interact with humans, there is an increased risk of systems that can easily deceive and manipulate people. Preventing unintended deception and manipulation ...
- research-article
Uni[MASK]: unified inference in sequential decision problems
- Micah Carroll,
- Orr Paradise,
- Jessy Lin,
- Raluca Georgescu,
- Mingfei Sun,
- David Bignell,
- Stephanie Milani,
- Katja Hofmann,
- Matthew Hausknecht,
- Anca Dragan,
- Sam Devlin
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems•November 2022, Article No.: 2563, pp 35365-35378Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making, where many ...
- research-article
Characterizing Manipulation from AI Systems
EAAMO '23: Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization•October 2023, Article No.: 6, pp 1-13• https://doi.org/10.1145/3617694.3623226Manipulation is a concern in many domains, such as social media, advertising, and chatbots. As AI systems mediate more of our digital interactions, it is important to understand the degree to which AI systems might manipulate humans without the intent ...
- research-article
Who needs to know? minimal knowledge for optimal coordination
ICML'23: Proceedings of the 40th International Conference on Machine Learning•July 2023, Article No.: 768, pp 18599-18613To optimally coordinate with others in cooperative games, it is often crucial to have information about one's collaborators: successful driving requires understanding which side of the road to drive on. However, not every feature of collaborators is ...
- research-article
Harms from Increasingly Agentic Algorithmic Systems
- Alan Chan,
- Rebecca Salganik,
- Alva Markelius,
- Chris Pang,
- Nitarshan Rajkumar,
- Dmitrii Krasheninnikov,
- Lauro Langosco,
- Zhonghao He,
- Yawen Duan,
- Micah Carroll,
- Michelle Lin,
- Alex Mayhew,
- Katherine Collins,
- Maryam Molamohammadi,
- John Burden,
- Wanru Zhao,
- Shalaleh Rismani,
- Konstantinos Voudouris,
- Umang Bhatt,
- Adrian Weller,
- David Krueger,
- Tegan Maharaj
FAccT '23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency•June 2023, pp 651-666• https://doi.org/10.1145/3593013.3594033Research in Fairness, Accountability, Transparency, and Ethics (FATE)1 has established many sources and forms of algorithmic harm, in domains as diverse as health care, finance, policing, and recommendations. Much work remains to be done to mitigate the ...
- extended-abstract
Estimating and Penalizing Preference Shift in Recommender Systems
RecSys '21: Proceedings of the 15th ACM Conference on Recommender Systems•September 2021, pp 661-667• https://doi.org/10.1145/3460231.3478849Recommender systems trained via long-horizon optimization (e.g., reinforcement learning) will have incentives to actively manipulate user preferences through the recommended content. While some work has argued for making systems myopic to avoid this ...
- extended-abstract
Evaluating the Robustness of Collaborative Agents
AAMAS '21: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems•May 2021, pp 1560-1562Artificial 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 ...
- research-article
On the utility of learning about humans for human-AI coordination
NIPS'19: Proceedings of the 33rd International Conference on Neural Information Processing Systems•December 2019, Article No.: 465, pp 5174-5185While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can ...