Skip to content
Back to skills

Graying The Black Box Understanding Dqns

ASecurity

**arXiv ID:** 1602.02658 **Authors:** Tom Zahavy, Nir Ben Zrihem, Shie Mannor **Published:** 2016-02-08T17:27:31Z **Abstract:** In recent years there is a growing interest in using deep representations for reinforcement learning. In this paper, we present a methodology and tools to analyze Deep Q-networks (DQNs) in a non-blind matter. Moreover, we propose a new model, the Semi Aggregated Markov Decision Process (SAMDP), and an algorithm that learns it automatically. The SAMDP model allows us ...

  • 3 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added September 11, 2026
toolsgo

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill graying-the-black-box-understanding-dqns --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Graying The Black Box Understanding Dqns?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Graying The Black Box Understanding Dqns
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-graying-the-black-box-understanding-dqns/badge)](https://www.skillsdirectory.com/skills/hiyenwong-graying-the-black-box-understanding-dqns)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Graying the black box: Understanding DQNs

**arXiv ID:** 1602.02658
**Authors:** Tom Zahavy, Nir Ben Zrihem, Shie Mannor
**Published:** 2016-02-08T17:27:31Z
**Abstract:**
In recent years there is a growing interest in using deep representations for reinforcement learning. In this paper, we present a methodology and tools to analyze Deep Q-networks (DQNs) in a non-blind matter. Moreover, we propose a new model, the Semi Aggregated Markov Decision Process (SAMDP), and an algorithm that learns it automatically. The SAMDP model allows us to identify spatio-temporal abstractions directly from features and may be used as a sub-goal detector in future work. Using our tools we reveal that the features learned by DQNs aggregate the state space in a hierarchical fashion, explaining its success. Moreover, we are able to understand and describe the policies learned by DQNs for three different Atari2600 games and suggest ways to interpret, debug and optimize deep neural networks in reinforcement learning.

## Skill Description

This skill is generated from the arXiv paper: Graying the black box: Understanding DQNs (1602.02658).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1602.02658](http://arxiv.org/abs/1602.02658v4)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.