viralamo

Menu
  • Technology
  • Science
  • Money
  • Culturs
  • Trending
  • Video

Subscribe To Our Website To Receive The Last Stories

Join Us Now For Free
Home
Technology
OpenAI releases Safety Gym for reinforcement learning
Technology

OpenAI releases Safety Gym for reinforcement learning

24/11/2019

While much work in data science to date has focused on algorithmic scale and sophistication, safety — that is, safeguards against harm — is a domain no less worth pursuing. This is particularly true in applications like self-driving vehicles, where a machine learning system’s poor judgment might contribute to an accident.

That’s why firms like Intel’s Mobileye and Nvidia have proposed frameworks to guarantee safe and logical decision-making, and it’s why OpenAI — the San Francisco-based research firm cofounded by CTO Greg Brockman, chief scientist Ilya Sutskever, and others — today released Safety Gym. OpenAI describes it as a suite of tools for developing AI that respects safety constraints while training, and for comparing the “safety” of algorithms and the extent to which those algorithms avoid mistakes while learning.

Safety Gym is designed for reinforcement learning agents, or AI that’s progressively spurred toward goals via rewards (or punishments). They learn by trial and error, which can be a risky endeavor — the agents sometimes try dangerous behaviors that lead to errors.

As a remedy, OpenAI proposes a form of reinforcement learning called constrained reinforcement learning, which implements cost functions that the AI must constrain. In contrast to common practice, where an agent’s behavior is described by a function that’s tailored to favor objectives, constrained agents figure out trade-offs that achieve certain defined outcomes.

“In normal [reinforcement learning], you would pick the collision fine at the beginning of training and keep it fixed forever,” OpenAI explains in a blog post. “The problem here is that if the pay-per-trip is high enough, the agent may not care whether it gets in lots of collisions (as long as it can still complete its trips) … [But in] constrained [reinforcement learning,] you would pick the acceptable collision rate at the beginning of training, and adjust the collision fine until the agent is meeting that requirement.”

To this end, Safety Gym introduces environments that require AI agents — Point, Car, Doggo, or a custom design — to navigate cluttered environments to achieve a goal, button, or push task. There are two levels of difficulty, and each time an agent performs an action that’s unsafe (i.e., runs into clutter), a red warning light flashes around the agent and the agent incurs a cost.

Safety Gym ships with standard and constrained reinforcement learning algorithms out of the box in addition to the code used to run experiments, and OpenAI says that preliminary results demonstrate the range of difficulty in Safety Gym environments. The simplest environments are relatively easy to solve and allow for fast iteration, while the hardest environments might be too challenging for current techniques.

OpenAI leaves to future work improving performance on current Safety Gym environments, using Safety Gym to investigate safe AI training techniques, and combining constrained reinforcement learning with implicit specifications like human preferences. It also hopes to contribute to the formulation of a metric that might measure the safety of AI systems.

“[Safety metrics] could feasibly be integrated into assessment schemes that developers use to test their systems, and could potentially be used by the government to create standards for safety,” wrote OpenAI. “We … hope that systems like Safety Gym can make it easier for AI developers to collaborate on safety across the AI sector via work on open, shared systems.”

Source link

Share
Tweet
Pinterest
Linkedin
Stumble
Google+
Email
Prev Article
Next Article

Related Articles

PlayStation 5 gets Godfall looter-slasher from Gearbox Publishing
Evo is the biggest fighting game event of the year. …

Evo 2020 cancelled in wake of sexual abuse allegations (Updated)

Facebook bowed to a Singapore government order to brand a news post as false – TechCrunch
Facebook added a correction notice to a post by a …

Facebook bowed to a Singapore government order to brand a news post as false – TechCrunch

Leave a Reply Cancel reply

Find us on Facebook

Related Posts

  • GamesBeat Summit 2020 goes completely digital
    GamesBeat Summit Digital agenda — Scores of …
    25/03/2020
  • What an all-digital AI research conference looks like
    Researchers propose Falcon, a privacy-preserving communication protocol …
    10/04/2020
  • 2020 will be a big year for online childcare — here are 7 startups to watch
    The rise of the human-centric CEO
    06/05/2020
  • Zero Mass Water: How the water in the air can save us
    Zero Mass Water: How the water in …
    13/01/2020
  • HP Reverb G2 virtual reality headset arrives this fall for $600
    HP Reverb G2 virtual reality headset arrives …
    29/05/2020

Popular Posts

  • 10 People Who Suffer From Strange Phobias …
    19/06/2022 0
  • 10 Real Historical Events That Inspired ‘Game …
    22/05/2022 0
  • Top 10 ’90s Songs You Didn’t Realize …
    23/05/2022 0
  • Top 10 Mysteries, Cold Cases & Puzzles …
    23/05/2022 0
  • Ransomware attack on Planned Parenthood steals data of 400,000 patients
    Why it’s hard to sanction ransomware groups
    23/05/2022 0

viralamo

Pages

  • Contact Us
  • Privacy Policy
Copyright © 2022 viralamo
Theme by MyThemeShop.com

Ad Blocker Detected

Our website is made possible by displaying online advertisements to our visitors. Please consider supporting us by disabling your ad blocker.

Refresh