• Home
  • About Us
  • Contact Us
  • Privacy Policy
  • Special Offers
Business Intelligence Info
  • Business Intelligence
    • BI News and Info
    • Big Data
    • Mobile and Cloud
    • Self-Service BI
  • CRM
    • CRM News and Info
    • InfusionSoft
    • Microsoft Dynamics CRM
    • NetSuite
    • OnContact
    • Salesforce
    • Workbooks
  • Data Mining
    • Pentaho
    • Sisense
    • Tableau
    • TIBCO Spotfire
  • Data Warehousing
    • DWH News and Info
    • IBM DB2
    • Microsoft SQL Server
    • Oracle
    • Teradata
  • Predictive Analytics
    • FICO
    • KNIME
    • Mathematica
    • Matlab
    • Minitab
    • RapidMiner
    • Revolution
    • SAP
    • SAS/SPSS
  • Humor

Language may help AI navigate new environments

April 19, 2020   Big Data

In a new study published this week on the preprint server Arxiv.org, scientists at the University of Toronto and the Vector Institute, an independent nonprofit dedicated to advancing AI, propose BabyAI++, a platform to study whether descriptive texts help AI to generalize across dynamic environments. Both it and several baseline models will soon be available on GitHub.

One of the most powerful techniques in machine learning — reinforcement learning, which entails spurring software agents toward goals via rewards — is also one of the most flawed. It’s sample inefficient, meaning it requires a large number of compute cycles to complete, and without additional data to cover variations, it adapts poorly to environments that differ from the training environment.

It’s theorized that prior knowledge of tasks through structured language could be combined with reinforcement learning to mitigate its shortcomings, and BabyAI++ was designed to put this theory to the test. To this end, the platform builds upon an existing reinforcement learning framework — BabyAI — to generate various dynamic, color tile-based environments along with texts that describe their layouts in detail.

 Language may help AI navigate new environments

Above: Environments in BabyAI++.

BabyAI++’s levels consist of objects that can be picked up and dropped; doors that can be unlocked and opened; and various tasks that the agents must be undertake. Like the environments themselves, the tasks are randomly generated, and they’re communicated to the agent through “Baby-Language,” a compositional language that uses a subset of English vocabulary.

The abovementioned texts reveal which types of tiles are in use and what color is matched to each tile. Since the pairing between the color and tile type is randomized, the agent must understand the description for it to properly navigate the map.

 Language may help AI navigate new environments

Within BabyAI++, every level is partitioned into two configurations: training and testing. In the training configuration, the agent is exposed to all tile and colors types in the level, but some combinations of color-type pairs are held out. In the testing configuration, all color-type pairs are enabled, forcing the agent to use language grounding to associate the type of the tile to the color.

The paper describes several experiments that were conducted using the baseline models, one of which — attention-fusion — uses what’s called an attention mechanism to assign relevant text embeddings (mathematical representations) to locations on a scene embedding feature map (a function that maps embeddings to a feature space, or the dimensions where the variables the AI processes reside). For the most difficult level, this attention-fusion model had a 16.2% higher testing success rate (around 60% after 5 steps, or actions) than the second-best model on the most challenging level, and it completed the level using fewer frames of images (around 65 compared with 75).

 Language may help AI navigate new environments

Above: The attention model’s architecture.

The coauthors assert that this shows descriptive texts are useful for agents to generalize environments with variable dynamics by learning language-grounding. “We believe the proposed BabyAI++ platform, with its public code and baseline implementations, will further spur research development in this area,” they wrote in the paper.

Let’s block ads! (Why?)

Big Data – VentureBeat

Environments, help, language, Navigate
  • Recent Posts

    • We were upgraded to the Unified Interface for Dynamics 365. Now What?
    • Recreating Art – the unexpected way
    • Upcoming Webinar: Using Dynamics 365 to Empower your Marketing and Sales Teams with Digital Automation
    • Center for Applied Data Ethics suggests treating AI like a bureaucracy
    • Improving Dynamics 365 Data Integrations with Alternate Keys
  • Categories

  • Archives

    • January 2021
    • December 2020
    • November 2020
    • October 2020
    • September 2020
    • August 2020
    • July 2020
    • June 2020
    • May 2020
    • April 2020
    • March 2020
    • February 2020
    • January 2020
    • December 2019
    • November 2019
    • October 2019
    • September 2019
    • August 2019
    • July 2019
    • June 2019
    • May 2019
    • April 2019
    • March 2019
    • February 2019
    • January 2019
    • December 2018
    • November 2018
    • October 2018
    • September 2018
    • August 2018
    • July 2018
    • June 2018
    • May 2018
    • April 2018
    • March 2018
    • February 2018
    • January 2018
    • December 2017
    • November 2017
    • October 2017
    • September 2017
    • August 2017
    • July 2017
    • June 2017
    • May 2017
    • April 2017
    • March 2017
    • February 2017
    • January 2017
    • December 2016
    • November 2016
    • October 2016
    • September 2016
    • August 2016
    • July 2016
    • June 2016
    • May 2016
    • April 2016
    • March 2016
    • February 2016
    • January 2016
    • December 2015
    • November 2015
    • October 2015
    • September 2015
    • August 2015
    • July 2015
    • June 2015
    • May 2015
    • April 2015
    • March 2015
    • February 2015
    • January 2015
    • December 2014
    • November 2014
© 2021 Business Intelligence Info
Power BI Training | G Com Solutions Limited