正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Using reinforcement learning we have expanded the range of techniques the Ultra Mobile Vehicle (UMV) uses to handle terrain and obstacles, including hops, out-of-plane balance, and level-ground flips. Millions of physics-based simulations provide training data to support zero-shot transfers.

RAI Institute

7,855 subscribers

75,199 次观看 • 1 年前 •via X (Twitter)

科学技术游戏教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

RAI Institute

76,647 次观看 • 1 年前

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽ We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning. Here’s how. 🧵

Google DeepMind

447,987 次观看 • 2 年前

When asked if Egypt will provide troops on the ground in Gaza to help support its security and stabilization, Egyptian Foreign Minister Badr Abdelatty says, “Deployment of international force is on the table. We are supporting this idea, of course.” “We are going to support and to commit troops within specific parameters,” he tells Margaret Brennan. “We must have a mandate by the Security Council to endorse it. And of course, to specify the mission of the troops on the ground, which will be peacekeeping, and how to provide training to the Palestinian policemen, in order to do their job to have law enforcement on the ground.”

When asked if Egypt will provide troops on the ground in Gaza to help support its security and stabilization, Egyptian Foreign Minister Badr Abdelatty says, “Deployment of international force is on the table. We are supporting this idea, of course.” “We are going to support and to commit troops within specific parameters,” he tells Margaret Brennan. “We must have a mandate by the Security Council to endorse it. And of course, to specify the mission of the troops on the ground, which will be peacekeeping, and how to provide training to the Palestinian policemen, in order to do their job to have law enforcement on the ground.”

Face The Nation

22,993 次观看 • 10 个月前

Robots can now walk blind with Figure AI's Helix Walking Controller. Instead of using cameras, the controller relies on the robot's internal sensors and reinforcement learning to maintain balance while walking. The controller, unveiled last year, allows the robot to stay balanced, recover from pushes, and move confidently across difficult terrain.

Robots can now walk blind with Figure AI's Helix Walking Controller. Instead of using cameras, the controller relies on the robot's internal sensors and reinforcement learning to maintain balance while walking. The controller, unveiled last year, allows the robot to stay balanced, recover from pushes, and move confidently across difficult terrain.

Space and Technology

28,804 次观看 • 2 个月前

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,772 次观看 • 2 个月前

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 次观看 • 11 个月前

Course on Matrix Methods in Data Analysis & Signal Processing Machine Learning in Finance represents one of AI's fastest growing applications, leveraging data driven models and algorithms to make financial predictions, manage risks, and automate trading decisions. At the forefront is algorithmic trading (quant trading), where ML models predict price movements and execute high speed trades by learning from historical market data including prices, volume, and news sentiment using sophisticated techniques like reinforcement learning, regression analysis, decision trees, and LSTM neural networks to gain competitive advantages in increasingly complex financial markets

Course on Matrix Methods in Data Analysis & Signal Processing Machine Learning in Finance represents one of AI's fastest growing applications, leveraging data driven models and algorithms to make financial predictions, manage risks, and automate trading decisions. At the forefront is algorithmic trading (quant trading), where ML models predict price movements and execute high speed trades by learning from historical market data including prices, volume, and news sentiment using sophisticated techniques like reinforcement learning, regression analysis, decision trees, and LSTM neural networks to gain competitive advantages in increasingly complex financial markets

D4rsh🦅

82,499 次观看 • 1 年前

Simulating entry… Using our LAVA software, Ames engineers performed simulations of a conceptual Mars spacecraft during entry. Here, the vehicle travels at supersonic speed (Mach 2.4) and uses retro-propulsion to decelerate further.

Simulating entry… Using our LAVA software, Ames engineers performed simulations of a conceptual Mars spacecraft during entry. Here, the vehicle travels at supersonic speed (Mach 2.4) and uses retro-propulsion to decelerate further.

NASA Ames

79,461 次观看 • 19 天前

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Helix is now learning directly from human video data We have already trained on data collected in the real world, including Brookfield residential units To our knowledge, this is the first instance of a humanoid robot learning navigation end-to-end using only human video

Figure

46,041 次观看 • 11 个月前

👋 Wonderful to meet the community of Barking this morning! The King and Queen visited the Barking Learning Centre Community and Family Hub. This community-based learning facility houses Barking Library and brings together a range of council services, and local groups. 💬 Their Majesties spent time with families and staff, who work at the centre to provide advice on employment, support those who are homeless, and encourage reading in the library.

👋 Wonderful to meet the community of Barking this morning! The King and Queen visited the Barking Learning Centre Community and Family Hub. This community-based learning facility houses Barking Library and brings together a range of council services, and local groups. 💬 Their Majesties spent time with families and staff, who work at the centre to provide advice on employment, support those who are homeless, and encourage reading in the library.

The Royal Family

79,385 次观看 • 6 个月前

We open-sourced all components of the HTD whole-body controller (WBC): -Play our WBC on your browser: -Main HTD codebase entry: (data collection and HTD policy soon!) Highlighted features: -Lightweight decoupled WBC that can be trained on a single GPU -A stable control base for humanoid loco-manipulation (in a mobile-manipulation style) -Support a wide range of body poses including extreme ones -Isaac Sim/Lab training, zero-shot deployment

We open-sourced all components of the HTD whole-body controller (WBC): -Play our WBC on your browser: -Main HTD codebase entry: (data collection and HTD policy soon!) Highlighted features: -Lightweight decoupled WBC that can be trained on a single GPU -A stable control base for humanoid loco-manipulation (in a mobile-manipulation style) -Support a wide range of body poses including extreme ones -Isaac Sim/Lab training, zero-shot deployment

Yaru Niu

21,742 次观看 • 8 天前

We own 24 million users and 1 billion refined data records, and we plan to provide this data free of charge to all AI startup companies for one month. Meet Data Hedge now the most powerful LLM user-based data layer.

We own 24 million users and 1 billion refined data records, and we plan to provide this data free of charge to all AI startup companies for one month. Meet Data Hedge now the most powerful LLM user-based data layer.

DATAHEDGE

118,864 次观看 • 3 个月前

Trump: "We send hundreds of millions of gallons of water a day to the Pacific Ocean. They turn a valve and the valve heads out. And we turned the valve back. I actually had to do it using force. We turned the valve back and now they have water."

Trump: "We send hundreds of millions of gallons of water a day to the Pacific Ocean. They turn a valve and the valve heads out. And we turned the valve back. I actually had to do it using force. We turned the valve back and now they have water."

Aaron Rupar

2,703,115 次观看 • 1 年前

#webgi engine is revolutionizing the world of real time jewellery rendering! Using cutting-edge physics-based simulations, we can now create stunning virtual jewellery with jaw-dropping realism. Prepare to be mesmerized by the sparkle and shine! 💍✨ #PhysicsSimulation #JewelleryInnovation #threejs #webgl

#webgi engine is revolutionizing the world of real time jewellery rendering! Using cutting-edge physics-based simulations, we can now create stunning virtual jewellery with jaw-dropping realism. Prepare to be mesmerized by the sparkle and shine! 💍✨ #PhysicsSimulation #JewelleryInnovation #threejs #webgl

iJewel3D (Pixotronics)

15,756 次观看 • 3 年前

We support over 5.9 million Palestine Refugees. 30,000 of us do this. Day in, day out. We do it in: 📍Jordan 📍The Gaza Strip 📍The occupied West Bank, including East Jerusalem 📍Syria 📍Lebanon We are uniquely able to provide healthcare, learning, and more. Support UNRWA. Support Palestine Refugees. #UNRWAworks

We support over 5.9 million Palestine Refugees. 30,000 of us do this. Day in, day out. We do it in: 📍Jordan 📍The Gaza Strip 📍The occupied West Bank, including East Jerusalem 📍Syria 📍Lebanon We are uniquely able to provide healthcare, learning, and more. Support UNRWA. Support Palestine Refugees. #UNRWAworks

UNRWA

20,849 次观看 • 6 个月前

CHECK THIS OUT… How to lift millions of children out of poverty and aid middle-class families with the cost of raising kids: Kamala Harris’s plan to provide a $6,000 tax credit for parents of newborns as well as bringing back the pandemic-era expanded Child Tax Credit.

CHECK THIS OUT… How to lift millions of children out of poverty and aid middle-class families with the cost of raising kids: Kamala Harris’s plan to provide a $6,000 tax credit for parents of newborns as well as bringing back the pandemic-era expanded Child Tax Credit.

Christopher Webb

143,143 次观看 • 1 年前