7 papers
Quantifying Potential Observation Missingness in Inverse Reinforcement Learning
Leo Benac, Abhishek Sharma, Alihan Huyuk +1
Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants o…
Transparent Trade-offs between Properties of Explanations
Hiwot Belay Tadesse, Alihan Hüyük, Yaniv Yacoby +2
When explaining black-box machine learning models, it's often important for explanations to have certain desirable properties. Most existing methods `encourage' desirable propertie…
Compositional Causal Reasoning Evaluation in Language Models
Jacqueline R. M. A. Maasch, Alihan Hüyük, Xinnuo Xu +2
Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified pe…
Strategically Linked Decisions in Long-Term Planning and Reinforcement Learning
Alihan Hüyük, Finale Doshi-Velez
Long-term planning, as in reinforcement learning (RL), involves finding strategies: actions that collectively work toward a goal rather than individually optimizing their immediate…
Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning
Alihan Hüyük, Arndt Ryo Koblitz, Atefeh Mohajeri +1
In image-based reinforcement learning (RL), policies usually operate in two steps: first extracting lower-dimensional features from raw images (the "recognition" step), and then ta…
Reasoning Elicitation in Language Models via Counterfactual Feedback
Alihan Hüyük, Xinnuo Xu, Jacqueline Maasch +2
Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answeri…