Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks

by   Ruohan Zhang, et al.
The University of Texas at Austin

A longstanding goal of artificial intelligence is to create artificial agents capable of learning to perform tasks that require sequential decision making. Importantly, while it is the artificial agent that learns and acts, it is still up to humans to specify the particular task to be performed. Classical task-specification approaches typically involve humans providing stationary reward functions or explicit demonstrations of the desired tasks. However, there has recently been a great deal of research energy invested in exploring alternative ways in which humans may guide learning agents that may, e.g., be more suitable for certain tasks or require less human effort. This survey provides a high-level overview of five recent machine learning frameworks that primarily rely on human guidance apart from pre-specified reward functions or conventional, step-by-step action demonstrations. We review the motivation, assumptions, and implementation of each framework, and we discuss possible future research directions.


page 4

page 6

page 10

page 14

page 18

page 21

page 25

page 32


Leveraging Human Guidance for Deep Reinforcement Learning Tasks

Reinforcement learning agents can learn to solve sequential decision tas...

Human-in-the-loop Machine Learning: A Macro-Micro Perspective

Though technical advance of artificial intelligence and machine learning...

Visual Analytics for Explainable Deep Learning

Recently, deep learning has been advancing the state of the art in artif...

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

Although reinforcement learning has seen tremendous success recently, th...

A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges

In recent years, the development of robotics and artificial intelligence...

An Offline Time-aware Apprenticeship Learning Framework for Evolving Reward Functions

Apprenticeship learning (AL) is a process of inducing effective decision...

A Survey on the Explainability of Supervised Machine Learning

Predictions obtained by, e.g., artificial neural networks have a high ac...

Please sign up or login with your details

Forgot password? Click here to reset