Skip to content
Back to skills

Hindsight Experience Replay

ASecurity

**arXiv ID:** 1707.01495 **Authors:** Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, Wojciech Zaremba **Published:** 2017-07-05T17:55:53Z **Abstract:** Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the n...

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

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill hindsight-experience-replay --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hindsight Experience Replay?

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

Security grade badge for Hindsight Experience Replay
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-hindsight-experience-replay/badge)](https://www.skillsdirectory.com/skills/hiyenwong-hindsight-experience-replay)

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
# Hindsight Experience Replay

**arXiv ID:** 1707.01495
**Authors:** Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, Wojciech Zaremba
**Published:** 2017-07-05T17:55:53Z
**Abstract:**
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum.
  We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in each case using only binary rewards indicating whether or not the task is completed. Our ablation studies show that Hindsight Experience Replay is a crucial ingredient which makes training possible in these challenging environments. We show that our policies trained on a physics simulation can be deployed on a physical robot and successfully complete the task.

## Skill Description

This skill is generated from the arXiv paper: Hindsight Experience Replay (1707.01495).

## How to Use

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

## References

- [arXiv:1707.01495](http://arxiv.org/abs/1707.01495v3)

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.