您现在的位置是:NVIDIA’s breakthrough AI teaches robots human >>正文
NVIDIA’s breakthrough AI teaches robots human
上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛8人已围观
简介By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.Eureka, a...
By subscribing, you agree to our Terms of Use and Policies You may unsubscribe at any time.
Eureka, an artificial intelligence (AI) agent developed by the research team at chipmaker NVIDIA, can teach robots complex skills like rapidly spinning a pen at par with humans, a press release said. This is just one of the 30 tasks the robots have been taught using the AI agent.
NVIDIA, which is well known for its GPUs that made possible the training of ChatGPT, has also been working on its development platform, Omniverse, for building 3D tools and applications. Earlier this year, the company unveiled its Voyager AI agent that could build tools 15 times faster than other AI agents in Minecraft.
See Also Related- NVIDIA and Foxconn partner up to build ‘AI factories’ for future EVs
- Neuralangelo: Nvidia's new AI model turns 2D videos into 3D structures
- Nvidia is on track to becoming the first trillion-dollar chipmaker
The Voyager AI agent was built using the large language model (LLM) GPT-4, and the team at NVIDIA has now used the same model to create a new agent that can perform complex skills at par with humans.
How does Eureka work?
Reinforcement learning (RL) has been used extensively in AI for a few years. “Reinforcement learning has enabled impressive wins over the last decade, yet many challenges still exist, such as reward design, which remains a trial-and-error process,” said Anima Anandkumar, senior director of AI research at NVIDIA, in the press release.
Eureka goes a step further and works with generative AI to write software code that rewards robots through reinforcement learning. This is done using GPT-4 LLM and does not need task-specific prompting or a predefined template. Moreover, the agent can incorporate human feedback to modify rewards to improve the results.
Eureka's library of algorithms works can be used on Isaac Gym, NVIDIA's physics simulations reference application built on Omniverse and used for reinforcement learning research. Powered by NVIDIA's GPUs, the Isaac Gym can rapidly evaluate even large batches of reward candidates, further improving training efficiency.
The AI agent then prepares a summary fed into the LLM to improve reward functions using the critical stats from training results. The approach was used for a wide range of robot types, such as quadruped, bipedal, and quadrotor, with dexterous hands or cobot arms with equal ease.
The results generated from Isaac Gym environments can be visualized in NVIDIA Omniverse, showcased below.
How well does Eureka work?
Apart from rapid pen spinning, NVIDIA researchers successfully trained the robots to complete other complex tasks, such as opening cabinets and drawers, tossing and catching balls, and manipulating scissors.
According to a research paper by the NVIDIA team, Eureka-generated rewards outperformed human-written ones on more than 80 percent of the tasks performed. They led to more than 50 percent performance improvements in the robots.
The paper also lists performance improvements in in-depth evaluations of 20 tasks on which robots were trained using Eureka that involved complex manipulation skills.
NVIDIA is confident its recent progress will encourage developers to take up more ambitious and challenging projects shortly. "We believe that Eureka will enable dexterous robot control and provide a new way to produce physically realistic animations for artists," added Jim Fan, a senior research scientist at NVIDIA, who was involved in the research.
Tags:
转载:欢迎各位朋友分享到网络,但转载请说明文章出处“上海品茶网 - 夜上海最新论坛社区 - 上海千花论坛”。http://www.jz08.com.cn/news/115252.html
相关文章
Cake DeFi invests $100M in new corporate venture arm
NVIDIA’s breakthrough AI teaches robots humanCake DeFi, Singapore-based decentralized finance (DeFi) platform, has launched a new corporate ventu...
阅读更多
Aave V3 is live, with expansion to 6 blockchains including Polygon and Avalanche
NVIDIA’s breakthrough AI teaches robots humanAave V3 sees the leading DeFi lender expand beyond Avalanche, Ethereum, and Polygon.Aave, one of the...
阅读更多
You can now buy community token Shibnobi: here’s where
NVIDIA’s breakthrough AI teaches robots humanThe live price of Shibnobi, another Shiba-themed token, is $8.82E-15 with a 24-hour trading volume o...
阅读更多
热门文章
- More $4 billion worth of Bitcoin and Ethereum has been absorbed into DeFi so far.
- US Treasury Sec. Yellen says crypto innovation has a role in finance
- BitPay announced a permanent work from home policy yesterday
- Bitcoin struggles but Okcoin CEO thinks 3 catalysts will make it bullish
- The synthetic bitcoin market rises by 83% to hold over $700 million on the Ethereum blockchain
- Aptos Price Heading to the Moon as PancakeSwap TVL Soars
最新文章
Ethereum Classic eyes the $20 resistance level after its latest rally
AVAX trading volume down 20% today: Here’s where to buy
Origin Trail (TRAC/USD) Price Prediction
Bitcoin Cash (BCH) rises above $300 after the recent downturn
Australian regulator ASIC sues Finder Wallet
People want to see regulated firms that have major global accounting firms, says Circle's CEO