Autonomous Capability Assessment Of Sequential Decision-making Systems In Stochastic Settings (extended Version)
2023 · Pulkit Verma, Rushang Karia, Siddharth Srivastava
Abstract
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 is relatively understudied. This paper presents a new approach for modeling the capabilities of black-box AI systems that can plan and act, along with the possible effects and requirements for executing those capabilities in stochastic settings. We present an active-learning approach that can effectively interact with a black-box SDM system and learn an interpretable probabilistic model describing its capabilities. Theoretical analysis of the approach identifies the conditions under which the learning process is guaranteed to converge to the correct model of the agent; empirical evaluations on different agents and simulated scenarios show that this approach is few-shot generalizable and can effectively describe the capabilities of arbitrary black-box SDM agents in a samp
Authors
(none)
Tags
Stats
Related papers
- Act As You Learn: Adaptive Decision-making In Non-stationary Markov Decision Processes (2024)0.00
- A Framework For Adversarial Analysis Of Decision Support Systems Prior To Deployment (2025)0.00
- DSDF: An Approach To Handle Stochastic Agents In Collaborative Multi-agent Reinforcement Learning (2021)0.00
- Decision Making In Non-stationary Environments With Policy-augmented Search (2024)0.00
- Understanding Individual Decision-making In Multi-agent Reinforcement Learning: A Dynamical Systems Approach (2025)0.00
- Non-stationary Markov Decision Processes, A Worst-case Approach Using Model-based Reinforcement Learning, Extended Version (2019)0.00
- Decision Making In Non-stationary Environments With Policy-augmented Monte Carlo Tree Search (2022)0.00
- Learning To Make Adherence-aware Advice (2023)0.00