Skip to content
Back to skills

Rapid Tasksolving In Novel Environments

ASecurity

**arXiv ID:** 2006.03662 **Authors:** Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo **Published:** 2020-06-05T20:09:20Z **Abstract:** We propose the challenge of rapid task-solving in novel environments (RTS), wherein an agent must solve a series of tasks as rapidly as possible in an unfamiliar environment. An effective RTS agent must balance between exploring the unfamiliar environment and solving its current task, all while building a model of the ne...

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

Works with

  • api

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill rapid-tasksolving-in-novel-environments --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rapid Tasksolving In Novel Environments?

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

Security grade badge for Rapid Tasksolving In Novel Environments
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-rapid-tasksolving-in-novel-environments/badge)](https://www.skillsdirectory.com/skills/hiyenwong-rapid-tasksolving-in-novel-environments)

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
# Rapid Task-Solving in Novel Environments

**arXiv ID:** 2006.03662
**Authors:** Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo
**Published:** 2020-06-05T20:09:20Z
**Abstract:**
We propose the challenge of rapid task-solving in novel environments (RTS), wherein an agent must solve a series of tasks as rapidly as possible in an unfamiliar environment. An effective RTS agent must balance between exploring the unfamiliar environment and solving its current task, all while building a model of the new environment over which it can plan when faced with later tasks. While modern deep RL agents exhibit some of these abilities in isolation, none are suitable for the full RTS challenge. To enable progress toward RTS, we introduce two challenge domains: (1) a minimal RTS challenge called the Memory&Planning Game and (2) One-Shot StreetLearn Navigation, which introduces scale and complexity from real-world data. We demonstrate that state-of-the-art deep RL agents fail at RTS in both domains, and that this failure is due to an inability to plan over gathered knowledge. We develop Episodic Planning Networks (EPNs) and show that deep-RL agents with EPNs excel at RTS, outperforming the nearest baseline by factors of 2-3 and learning to navigate held-out StreetLearn maps within a single episode. We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience. algorithm and that they generalize to situations beyond their training experience.

## Skill Description

This skill is generated from the arXiv paper: Rapid Task-Solving in Novel Environments (2006.03662).

## How to Use

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

## References

- [arXiv:2006.03662](http://arxiv.org/abs/2006.03662v3)

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.