DeepAI AI Chat
Log In Sign Up

A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning

by   Amy Zhang, et al.

The risks and perils of overfitting in machine learning are well known. However most of the treatment of this, including diagnostic tools and remedies, was developed for the supervised learning case. In this work, we aim to offer new perspectives on the characterization and prevention of overfitting in deep Reinforcement Learning (RL) methods, with a particular focus on continuous domains. We examine several aspects, such as how to define and diagnose overfitting in MDPs, and how to reduce risks by injecting sufficient training diversity. This work complements recent findings on the brittleness of deep RL methods and offers practical observations for RL researchers and practitioners.


page 5

page 7

page 12

page 15

page 16

page 17

page 18


A Study on Overfitting in Deep Reinforcement Learning

Recent years have witnessed significant progresses in deep Reinforcement...

Diagnosing Bottlenecks in Deep Q-learning Algorithms

Q-learning methods represent a commonly used class of algorithms in rein...

The Primacy Bias in Deep Reinforcement Learning

This work identifies a common flaw of deep reinforcement learning (RL) a...

Vizarel: A System to Help Better Understand RL Agents

Visualization tools for supervised learning have allowed users to interp...

On overfitting and asymptotic bias in batch reinforcement learning with partial observability

This paper stands in the context of reinforcement learning with partial ...

Interactive Visualization for Debugging RL

Visualization tools for supervised learning allow users to interpret, in...

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels

Off-policy reinforcement learning (RL) from pixel observations is notori...