Discovering and Learning Probabilistic Models of Black-Box AI Capabilities

• URL: http://arxiv.org/abs/2512.16733v2
• Date: Sat, 20 Dec 2025 18:26:12 GMT
• Title: Discovering and Learning Probabilistic Models of Black-Box AI Capabilities
• Authors: Daniel Bramblett, Rushang Karia, Adrian Ciotinga, Ruthvick Suresh, Pulkit Verma, YooJung Choi, Siddharth Srivastava,
• Abstract summary: Black-box AI (BBAI) systems are increasingly being used for sequential decision making.<n>This paper shows that PDDL-style representations can be used to efficiently learn and model an input BBAI's planning capabilities.
• Score: 17.814540838646188
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Black-box AI (BBAI) systems such as foundational models are increasingly being used for sequential decision making. To ensure that such systems are safe to operate and deploy, it is imperative to develop efficient methods that can provide a sound and interpretable representation of the BBAI's capabilities. This paper shows that PDDL-style representations can be used to efficiently learn and model an input BBAI's planning capabilities. It uses the Monte-Carlo tree search paradigm to systematically create test tasks, acquire data, and prune the hypothesis space of possible symbolic models. Learned models describe a BBAI's capabilities, the conditions under which they can be executed, and the possible outcomes of executing them along with their associated probabilities. Theoretical results show soundness, completeness and convergence of the learned models. Empirical results with multiple BBAI systems illustrate the scope, efficiency, and accuracy of the presented methods.

Related papers

• Active Learning of Model Discrepancy with Bayesian Experimental Design [0.0]
  We propose an efficient approach to learn the model discrepancy based on the data from a sequential experimental design (BED)<n>We show that the proposed method is efficient and robust to the active learning of high-dimensional model discrepancy, using data suggested by the sequential BED.<n>We also demonstrate that the proposed method is compatible with both classical numerical solvers and modern auto-differentiable solvers.
  arXiv  Detail & Related papers  (2025-02-07T22:54:20Z)
• Supervised Score-Based Modeling by Gradient Boosting [49.556736252628745]
  We propose a Supervised Score-based Model (SSM) which can be viewed as a gradient boosting algorithm combining score matching.<n>We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy.<n>Our model outperforms existing models in both accuracy and inference time.
  arXiv  Detail & Related papers  (2024-11-02T07:06:53Z)
• SynthTree: Co-supervised Local Model Synthesis for Explainable Prediction [15.832975722301011]
  We propose a novel method to enhance explainability with minimal accuracy loss. We have developed novel methods for estimating nodes by leveraging AI techniques. Our findings highlight the critical role that statistical methodologies can play in advancing explainable AI.
  arXiv  Detail & Related papers  (2024-06-16T14:43:01Z)
• Gaussian Mixture Models for Affordance Learning using Bayesian Networks [50.18477618198277]
  Affordances are fundamental descriptors of relationships between actions, objects and effects. This paper approaches the problem of an embodied agent exploring the world and learning these affordances autonomously from its sensory experiences.
  arXiv  Detail & Related papers  (2024-02-08T22:05:45Z)
• Value function estimation using conditional diffusion models for control [62.27184818047923]
  We propose a simple algorithm called Diffused Value Function (DVF) It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model. We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
  arXiv  Detail & Related papers  (2023-06-09T18:40:55Z)
• Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version) [27.825419721676766]
  It is essential for users to understand what their AI systems can and can't do in order to use them safely. This paper presents a new approach for modeling the capabilities of black-box AI systems that can plan and act.
  arXiv  Detail & Related papers  (2023-06-07T22:05:48Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Feeding What You Need by Understanding What You Learned [54.400455868448695]
  Machine Reading (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-size models and corpus to improve the performance evaluated by metrics such as Exact Match. We argue that a deep understanding of model capabilities and data properties can help us feed a model with appropriate training data.
  arXiv  Detail & Related papers  (2022-03-05T14:15:59Z)
• Provably Robust Model-Centric Explanations for Critical Decision-Making [14.367217955827002]
  We show that data-centric methods may yield brittle explanations of limited practical utility. The model-centric framework, however, can offer actionable insights into risks of using AI models in practice.
  arXiv  Detail & Related papers  (2021-10-26T18:05:49Z)
• Active Learning of Markov Decision Processes using Baum-Welch algorithm (Extended) [0.0]
  This paper revisits and adapts the classic Baum-Welch algorithm for learning Markov decision processes and Markov chains. We empirically compare our approach with state-of-the-art tools and demonstrate that the proposed active learning procedure can significantly reduce the number of observations required to obtain accurate models.
  arXiv  Detail & Related papers  (2021-10-06T18:54:19Z)
• Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning [93.1435980666675]
  We show how optimistic exploration can be easily combined with state-of-the-art reinforcement learning algorithms. Our experiments demonstrate that optimistic exploration significantly speeds-up learning when there are penalties on actions.
  arXiv  Detail & Related papers  (2020-06-15T18:37:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.