SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.09464 · 2018

Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent is told what to do using an additional input. The second part of the paper presents a set of concrete research ideas for improving RL algorithms, most of which are related to Multi-Goal RL and Hindsight Experience Replay.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1802.09464")
get_code_for_paper("1802.09464")
have("1802.09464")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1802.09464.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1802.09464.svg)](https://syntology.ai/paper/1802.09464)

Connect an agent — have() is free.