Exploring Computational User Models for Agent Policy Summarization

05/30/2019
by   Isaac Lage, et al.
0

AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.

READ FULL TEXT

page 5

page 9

research
02/05/2021

"I Don't Think So": Disagreement-Based Policy Summaries for Comparing Agents

With Artificial Intelligence on the rise, human interaction with autonom...
research
07/29/2020

Compare and Select: Video Summarization with Multi-Agent Reinforcement Learning

Video summarization aims at generating concise video summaries from the ...
research
05/18/2020

Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps

With advances in reinforcement learning (RL), agents are now being devel...
research
11/09/2020

Automatic Summarization of Open-Domain Podcast Episodes

We present implementation details of our abstractive summarizers that ac...
research
01/29/2022

Explaining Reinforcement Learning Policies through Counterfactual Trajectories

In order for humans to confidently decide where to employ RL agents for ...
research
05/18/2021

PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies

We propose a novel reinforcement learning based framework PoBRL for solv...
research
07/12/2019

Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation

Reinforcement learning aims at searching the best policy model for decis...

Please sign up or login with your details

Forgot password? Click here to reset