Competency Assessment for Autonomous Agents using Deep Generative Models
This addresses the need for trustworthy human-agent partnerships by providing a method for precise competency assessment, though it appears incremental as it builds on existing deep generative techniques.
The paper tackled the problem of enabling autonomous agents to reliably communicate their competency for tasks by developing probabilistic world models using deep generative models, which simulate agent trajectories and calculate task outcome probabilities, achieving accurate competency assessment.
For autonomous agents to act as trustworthy partners to human users, they must be able to reliably communicate their competency for the tasks they are asked to perform. Towards this objective, we develop probabilistic world models based on deep generative modelling that allow for the simulation of agent trajectories and accurate calculation of tasking outcome probabilities. By combining the strengths of conditional variational autoencoders with recurrent neural networks, the deep generative world model can probabilistically forecast trajectories over long horizons to task completion. We show how these forecasted trajectories can be used to calculate outcome probability distributions, which enable the precise assessment of agent competency for specific tasks and initial settings.