Interpretable Apprenticship Learning with Temporal Logic Specifications
نویسندگان
چکیده
Recent work has addressed using formulas in linear temporal logic (LTL) as specifications for agents planning in Markov Decision Processes (MDPs). We consider the inverse problem: inferring an LTL specification from demonstrated behavior trajectories in MDPs. We formulate this as a multiobjective optimization problem, and describe state-based (“what actually happened”) and action-based (“what the agent expected to happen”) objective functions based on a notion of “violation cost”. We demonstrate the efficacy of the approach by employing genetic programming to solve this problem in two simple domains.
منابع مشابه
A NOTE TO INTERPRETABLE FUZZY MODELS AND THEIR LEARNING
In this paper we turn the attention to a well developed theory of fuzzy/lin-guis-tic models that are interpretable and, moreover, can be learned from the data.We present four different situations demonstrating both interpretability as well as learning abilities of these models.
متن کاملLogic meets Probability: Towards Explainable AI Systems for Uncertain Worlds
Logical AI is concerned with formal languages to represent and reason with qualitative specifications; statistical AI is concerned with learning quantitative specifications from data. To combine the strengths of these two camps, there has been exciting recent progress on unifying logic and probability. We review the many guises for this union, while emphasizing the need for a formal language to...
متن کاملProbably Approximately Correct MDP Learning and Control With Temporal Logic Constraints
We consider synthesis of controllers that maximize the probability of satisfying given temporal logic specifications in unknown, stochastic environments. We model the interaction between the system and its environment as a Markov decision process (MDP) with initially unknown transition probabilities. The solution we develop builds on the so-called model-based probably approximately correct Mark...
متن کاملDealing With Temporal Holes in Instructional ITS’s
Instructional Design, the technique typically used to design Computer Based Education software, including Intelligent Tutoring Systems, relies on a set of correctness metrics called Instructional Integrity. Hereby, pedagogical curricula should describe, in unambiguous, predictable, and measurable terms, what the student must do to demonstrate an understanding of course material. Computer Tutor ...
متن کاملSafe Control under Uncertainty
Controller synthesis for hybrid systems that satisfy temporal specifications expressing various system properties is a challenging problem that has drawn the attention of many researchers. However, making the assumption that such temporal properties are deterministic is far from the reality. For example, many of the properties the controller has to satisfy are learned through machine learning t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1710.10532 شماره
صفحات -
تاریخ انتشار 2017