DeepAI AI Chat
Log In Sign Up

Analyzing Knowledge Transfer in Deep Q-Networks for Autonomously Handling Multiple Intersections

05/02/2017
by   David Isele, et al.
0

We analyze how the knowledge to autonomously handle one type of intersection, represented as a Deep Q-Network, translates to other types of intersections (tasks). We view intersection handling as a deep reinforcement learning problem, which approximates the state action Q function as a deep neural network. Using a traffic simulator, we show that directly copying a network trained for one type of intersection to another type of intersection decreases the success rate. We also show that when a network that is pre-trained on Task A and then is fine-tuned on a Task B, the resulting network not only performs better on the Task B than an network exclusively trained on Task A, but also retained knowledge on the Task A. Finally, we examine a lifelong learning setting, where we train a single network on five different types of intersections sequentially and show that the resulting network exhibited catastrophic forgetting of knowledge on previous tasks. This result suggests a need for a long-term memory component to preserve knowledge.

READ FULL TEXT

page 1

page 3

page 5

11/30/2017

Transferring Autonomous Driving Knowledge on Simulated and Real Intersections

We view intersection handling on autonomous vehicles as a reinforcement ...
11/28/2017

Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task

In the present work we propose a Deep Feed Forward network architecture ...
05/20/2019

Continual Learning in Deep Neural Network by Using a Kalman Optimiser

Learning and adapting to new distributions or learning new tasks sequent...
12/19/2019

Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation

Enabling a neural network to sequentially learn multiple tasks is of gre...
12/04/2018

Overcoming Catastrophic Forgetting by Soft Parameter Pruning

Catastrophic forgetting is a challenge issue in continual learning when ...
11/15/2017

PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

This paper presents a method for adding multiple tasks to a single deep ...
01/22/2019

Use of First and Third Person Views for Deep Intersection Classification

We explore the problem of intersection classification using monocular on...