Feature-Based Interpretable Reinforcement Learning based on State-Transition Models

05/14/2021
by   Omid Davoodi, et al.
0

Growing concerns regarding the operational usage of AI models in the real-world has caused a surge of interest in explaining AI models' decisions to humans. Reinforcement Learning is not an exception in this regard. In this work, we propose a method for offering local explanations on risk in reinforcement learning. Our method only requires a log of previous interactions between the agent and the environment to create a state-transition model. It is designed to work on RL environments with either continuous or discrete state and action spaces. After creating the model, actions of any agent can be explained in terms of the features most influential in increasing or decreasing risk or any other desirable objective function in the locality of the agent. Through experiments, we demonstrate the effectiveness of the proposed method in providing such explanations.

READ FULL TEXT
research
11/10/2020

What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes

We present a novel form of explanation for Reinforcement Learning, based...
research
05/06/2023

Explaining RL Decisions with Trajectories

Explanation is a key component for the adoption of reinforcement learnin...
research
09/01/2020

PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning

Storyline visualizations are an effective means to present the evolution...
research
12/16/2021

Inherently Explainable Reinforcement Learning in Natural Language

We focus on the task of creating a reinforcement learning agent that is ...
research
10/11/2020

Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions

We investigate a deep reinforcement learning (RL) architecture that supp...
research
04/08/2018

Hierarchical Modular Reinforcement Learning Method and Knowledge Acquisition of State-Action Rule for Multi-target Problem

Hierarchical Modular Reinforcement Learning (HMRL), consists of 2 layere...
research
09/28/2015

Efficient Empowerment

Empowerment quantifies the influence an agent has on its environment. Th...

Please sign up or login with your details

Forgot password? Click here to reset