paper-with-me

Papers

Discovering User-Interpretable Capabilities of Black-Box Planning Agents

2021-07-28 · Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

Several approaches have been developed for answering users' specific questions about AI behavior and for assessing their core functionality in terms of primitive executable actions. However, the problem of summarizing an AI agent's broad capabilities for a user is comparatively new. This paper presents an algorithm for discovering from scratch the suite of high-level "capabilities" that an AI system with arbitrary internal planning algorithms/policies can perform. It computes conditions describing the applicability and effects of these capabilities in user-interpretable terms. Starting from a set of user-interpretable state properties, an AI agent, and a simulator that the agent can interact with, our algorithm returns a set of high-level capabilities with their parameterized descriptions. Empirical evaluation on several game-based scenarios shows that this approach efficiently learns descriptions of various types of AI agents in deterministic, fully observable settings. User studies show that such descriptions are easier to understand and reason with than the agent's primitive actions.

📄 PDF Abstract BibTeX arXiv:2107.13668

Code (1)

aair-lab/capability-discovery 공식 구현

Tasks

AI AgentDecision Making

Similar Papers 제목 키워드 기반

Efficient Black-Box Planning Using Macro-Actions with Focused Effects

2020-04-28 · Cameron Allen, Michael Katz, Tim Klinger, George Konidaris 외

The difficulty of deterministic planning increases exponentially with search-tree depth. Black-box planning presents an even greater challenge, since planners must operate without an explicit model of the domain. Heurist…

Asking the Right Questions: Learning Interpretable Action Models Through Query Answering

2019-12-29 · Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a min…

Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version)

2023-06-07 · Pulkit Verma, Rushang Karia, Siddharth Srivastava

It is essential for users to understand what their AI systems can and can't do in order to use them safely. However, the problem of enabling users to assess AI systems with sequential decision-making (SDM) capabilities i…

Active LearningDecision MakingSequential Decision Making

Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings

2023-09-21 · NeurIPS 2023 11

It is essential for users to understand what their AI systems can and can't do in order to use them safely. However, the problem of enabling users to assess AI systems with sequential decision-making (SDM) capabilities i…

SwissNYF: Tool Grounded LLM Agents for Black Box Setting

2024-02-15 · Somnath Sendhil Kumar, Dhruv Jain, Eshaan Agarwal, Raunak Pandey

While Large Language Models (LLMs) have demonstrated enhanced capabilities in function-calling, these advancements primarily rely on accessing the functions' responses. This methodology is practical for simpler APIs but …

Program SynthesisTrajectory Planning