Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task

2021-08-18 · Angel Ayala, Francisco Cruz, Bruno Fernandes, Richard Dazeley

Explainable reinforcement learning allows artificial agents to explain their behavior in a human-like manner aiming at non-expert end-users. An efficient alternative of creating explanations is to use an introspection-based method that transforms Q-values into probabilities of success used as the base to explain the agent's decision-making process. This approach has been effectively used in episodic and discrete scenarios, however, to compute the probability of success in non-episodic and more complex environments has not been addressed yet. In this work, we adapt the introspection method to be used in a non-episodic task and try it in a continuous Atari game scenario solved with the Rainbow algorithm. Our initial results show that the probability of success can be computed directly from the Q-values for all possible actions.

📄 PDF Abstract BibTeX arXiv:2108.08911

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep Reinforcement Learningreinforcement-learning Reinforcement Learning (RL)

Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios

2022-11-23 · Niclas Schroeter, Francisco Cruz, Stefan Wermter

With the increasing presence of robotic systems and human-robot environments in today's society, understanding the reasoning behind actions taken by a robot is becoming more important. To increase this understanding, use…

reinforcement-learning Reinforcement Learning (RL)

Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenario

2020-06-24 · Francisco Cruz, Richard Dazeley, Peter Vamplew, Ithan Moreira

Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To in…

Action Understanding Decision Making reinforcement-learning Reinforcement Learning+1

Generative Counterfactual Introspection for Explainable Deep Learning

2019-07-06 · Shusen Liu, Bhavya Kailkhura, Donald Loveland, Yong Han

In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fund…

counterfactual Deep Learning

Efficient Planning in Reinforcement Learning via Model Introspection

2026-02-07 · Gabriel Stella arxiv

Reinforcement learning and classical planning are typically seen as two distinct problems, with differing formulations necessitating different solutions. Yet, when humans are given a task, regardless of the way it is spe…

Reinforcement Learning

Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making

2023-06-06 · Mahault Albarracin, Inês Hipólito, Safae Essafi Tremblay, Jason G. Fox 외

This paper investigates the prospect of developing human-interpretable, explainable artificial intelligence (AI) systems based on active inference and the free energy principle. We first provide a brief overview of activ…

Decision Making Explainable artificial intelligence