Conveying Autonomous Robot Capabilities through Contrasting Behaviour Summaries

04/01/2023
by   Peter Du, et al.
0

As advances in artificial intelligence enable increasingly capable learning-based autonomous agents, it becomes more challenging for human observers to efficiently construct a mental model of the agent's behaviour. In order to successfully deploy autonomous agents, humans should not only be able to understand the individual limitations of the agents but also have insight on how they compare against one another. To do so, we need effective methods for generating human interpretable agent behaviour summaries. Single agent behaviour summarization has been tackled in the past through methods that generate explanations for why an agent chose to pick a particular action at a single timestep. However, for complex tasks, a per-action explanation may not be able to convey an agents global strategy. As a result, researchers have looked towards multi-timestep summaries which can better help humans assess an agents overall capability. More recently, multi-step summaries have also been used for generating contrasting examples to evaluate multiple agents. However, past approaches have largely relied on unstructured search methods to generate summaries and require agents to have a discrete action space. In this paper we present an adaptive search method for efficiently generating contrasting behaviour summaries with support for continuous state and action spaces. We perform a user study to evaluate the effectiveness of the summaries for helping humans discern the superior autonomous agent for a given task. Our results indicate that adaptive search can efficiently identify informative contrasting scenarios that enable humans to accurately select the better performing agent with a limited observation time budget.

READ FULL TEXT

page 1

page 6

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
09/02/2010

Automatable Evaluation Method Oriented toward Behaviour Believability for Video Games

Classic evaluation methods of believable agents are time-consuming becau...
research
03/13/2021

Delegation to autonomous agents promotes cooperation in collective-risk dilemmas

Home assistant chat-bots, self-driving cars, drones or automated negotia...
research
01/28/2020

Distal Explanations for Explainable Reinforcement Learning Agents

Causal explanations present an intuitive way to understand the course of...
research
04/10/2019

Is Two Better than One? Effects of Multiple Agents on User Persuasion

Virtual humans need to be persuasive in order to promote behaviour chang...
research
02/06/2021

An Autonomous Negotiating Agent Framework with Reinforcement Learning Based Strategies and Adaptive Strategy Switching Mechanism

Despite abundant negotiation strategies in literature, the complexity of...
research
01/27/2018

Understanding Deep Architectures by Interpretable Visual Summaries

A consistent body of research investigates the recurrent visual patterns...

Please sign up or login with your details

Forgot password? Click here to reset