Collaborating Authors

What is Machine Behavior?


Understanding the behavior of artificial intelligence(AI) agents is one of the pivotal challenges of the next decade of AI. Interpretability or explainability are some of the terms often used to describe methods that provide insights about the behavior of AI programs. Until today, most of the interpretability techniques have focused on exploring the internal structure of deep neural networks. Recently, a group of AI researchers from the Massachusetts Institute of Technology(MIT) are exploring a radical approach that attempts to explain the behavior of AI observing them in the same we study human or animal behavior. They group the ideas in this area under the catchy name of machine behavior which promises to be one of the most exciting fields in the next few years of AI.

Prediction and Behavior Modeling Research Scientist


Our Autonomous Mobility team is focused on developing and commercializing self-driving cars and systems that enable point-to-point mobility in challenging urban driving environments. With talented teams working across the globe in Boston, Pittsburgh, Las Vegas, Santa Monica, and Singapore, Aptiv is the first company to deploy commercial robotaxis to the public. Today, Aptiv has provided over 80,000 autonomous rides to members of the public passengers in Las Vegas -- the world's largest public deployment of self-driving vehicles. In September 2019, Aptiv announced a 50/50 joint venture with Hyundai Motor Group, bringing together HMG and Aptiv's advanced engineering and R&D capabilities, our global footprint, and shared commitment to advancing autonomous driving technology. Come work with leading engineers, research scientists, marketers and business development experts, all while enabling the future of mobility!


AAAI Conferences

Inverse reinforcement learning (IRL) aims to recover the reward function underlying a Markov Decision Process from behaviors of experts in support of decision-making. Most recent work on IRL assumes the same level of trustworthiness of all expert behaviors, and frames IRL as a process of seeking reward function that makes those behaviors appear (near)-optimal. However, it is common in reality that noisy expert behaviors disobeying the optimal policy exist, which may degrade the IRL performance significantly. To address this issue, in this paper, we develop a robust IRL framework that can accurately estimate the reward function in the presence of behavior noise. In particular, we focus on a special type of behavior noise referred to as sparse noise due to its wide popularity in real-world behavior data. To model such noise, we introduce a novel latent variable characterizing the reliability of each expert action and use Laplace distribution as its prior. We then devise an EM algorithm with a novel variational inference procedure in the E-step, which can automatically identify and remove behavior noise in reward learning. Experiments on both synthetic data and real vehicle routing data with noticeable behavior noise show significant improvement of our method over previous approaches in learning accuracy, and also show its power in de-noising behavior data.

Oh deer: Monkey caught in flagrante delict-doe

The Japan Times

PARIS – Scientists on Tuesday revealed the "highly unusual" behavior of a male monkey filmed trying to have sex with female deer in Japan -- a rare case of inter-species nookie. Sex between animals from different species is uncommon, but exceptional cases are known to occur, chiefly in domesticated and captive animals, scientists reported in the journal Primates. Mating is usually driven by the need to procreate, while sex across the species line is mostly fruitless or yields sterile offspring. For the new study -- only the second on the phenomenon of inter-species sex -- a Japanese macaque, or "snow monkey," was filmed mounting at least two female Sika deer much larger than itself. Without penetration, the young monkey makes sexual movements while riding on the does' backs on Yakushima Island.

African ants march into battle with termites and rescue their wounded comrades: scientists

The Japan Times

WASHINGTON – Much like human soldiers in combat, members of a large, black, termite-eating ant species found in sub-Saharan Africa march in formation into battle and afterward retrieve wounded comrades and carry them back home to recover. Scientists on Wednesday described the unique rescue behavior of the African Matabele ants, called Megaponera analis, after observing them in Cote d'Ivoire's Comoé National Park, but did not ascribe charitable motives to the insects. "This is not an altruistic behavior," said entomologist Erik Frank of the University of Würzburg in Germany, who led the research published in the journal Science Advances. "The ants do not help the injured out of the goodness of their hearts. There is a clear benefit for the colony: these injured ants are able to participate again in future raids and remain a functioning member of the colony."