Inherently Explainable Reinforcement Learning in Natural Language

12/16/2021
by   Xiangyu Peng, et al.
0

We focus on the task of creating a reinforcement learning agent that is inherently explainable – with the ability to produce immediate local explanations by thinking out loud while performing a task and analyzing entire trajectories post-hoc to produce causal explanations. This Hierarchically Explainable Reinforcement Learning agent (HEX-RL), operates in Interactive Fictions, text-based game environments in which an agent perceives and acts upon the world using textual natural language. These games are usually structured as puzzles or quests with long-term dependencies in which an agent must complete a sequence of actions to succeed – providing ideal environments in which to test an agent's ability to explain its actions. Our agent is designed to treat explainability as a first-class citizen, using an extracted symbolic knowledge graph-based state representation coupled with a Hierarchical Graph Attention mechanism that points to the facts in the internal graph representation that most influenced the choice of actions. Experiments show that this agent provides significantly improved explanations over strong baselines, as rated by human participants generally unfamiliar with the environment, while also matching state-of-the-art task performance.

READ FULL TEXT

page 8

page 9

page 15

page 16

research
06/17/2021

Learning Knowledge Graph-based World Models of Textual Environments

World models improve a learning agent's ability to efficiently operate i...
research
01/23/2020

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

Interactive Fiction games are text-based simulations in which an agent i...
research
05/04/2023

Explainable Reinforcement Learning via a Causal World Model

Generating explanations for reinforcement learning (RL) is challenging a...
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
05/14/2021

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

Growing concerns regarding the operational usage of AI models in the rea...
research
02/13/2021

Mitigating Negative Side Effects via Environment Shaping

Agents operating in unstructured environments often produce negative sid...
research
04/16/2019

Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement Learning

Using touch devices to navigate in virtual 3D environments such as compu...

Please sign up or login with your details

Forgot password? Click here to reset