Skip to content
Back to skills

Towards Empathic Deep Qlearning

ASecurity

**arXiv ID:** 1906.10918 **Authors:** Bart Bussmann, Jacqueline Heinerman, Joel Lehman **Published:** 2019-06-26T08:59:02Z **Abstract:** As reinforcement learning (RL) scales to solve increasingly complex tasks, interest continues to grow in the fields of AI safety and machine ethics. As a contribution to these fields, this paper introduces an extension to Deep Q-Networks (DQNs), called Empathic DQN, that is loosely inspired both by empathy and the golden rule ("Do unto others as you would ha...

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

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill towards-empathic-deep-qlearning --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Towards Empathic Deep Qlearning?

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

Security grade badge for Towards Empathic Deep Qlearning
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-towards-empathic-deep-qlearning/badge)](https://www.skillsdirectory.com/skills/hiyenwong-towards-empathic-deep-qlearning)

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
# Towards Empathic Deep Q-Learning

**arXiv ID:** 1906.10918
**Authors:** Bart Bussmann, Jacqueline Heinerman, Joel Lehman
**Published:** 2019-06-26T08:59:02Z
**Abstract:**
As reinforcement learning (RL) scales to solve increasingly complex tasks, interest continues to grow in the fields of AI safety and machine ethics. As a contribution to these fields, this paper introduces an extension to Deep Q-Networks (DQNs), called Empathic DQN, that is loosely inspired both by empathy and the golden rule ("Do unto others as you would have them do unto you"). Empathic DQN aims to help mitigate negative side effects to other agents resulting from myopic goal-directed behavior. We assume a setting where a learning agent coexists with other independent agents (who receive unknown rewards), where some types of reward (e.g. negative rewards from physical harm) may generalize across agents. Empathic DQN combines the typical (self-centered) value with the estimated value of other agents, by imagining (by its own standards) the value of it being in the other's situation (by considering constructed states where both agents are swapped). Proof-of-concept results in two gridworld environments highlight the approach's potential to decrease collateral harms. While extending Empathic DQN to complex environments is non-trivial, we believe that this first step highlights the potential of bridge-work between machine ethics and RL to contribute useful priors for norm-abiding RL agents.

## Skill Description

This skill is generated from the arXiv paper: Towards Empathic Deep Q-Learning (1906.10918).

## How to Use

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

## References

- [arXiv:1906.10918](http://arxiv.org/abs/1906.10918v1)

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.