Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Matryoshka Representation Learning (MRL) is a super exciting approach to improving the quality and efficiency of embedding models and strategies ✨ MRL allows models to store more information in the earlier dimensions of their data vectors. This method not only boosts performance in tasks like classification and retrieval, but... show more

Victoria Slocum

9,880 subscribers

120,436 просмотров • 1 год назад •via X (Twitter)

Искусство Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 9

Фото профиля Parul Pandey

Parul Pandey1 год назад

Great video and explanation. Also love how you color-coded the equation to make it simple to understand 💡

Фото профиля Leonie

Leonie1 год назад

Love the new format! 🔥🔥🔥

Фото профиля Philip Vollet

Philip Vollet1 год назад

seesh 9000

Фото профиля Edward

Edward1 год назад

This video is

Фото профиля Suman Das 👨🏽‍💻 ⚽

Suman Das 👨🏽‍💻 ⚽1 год назад

Thanks for sharing 🙌

Фото профиля Radheshyam

Radheshyam1 год назад

Awesome explanation thanks 🙏

Фото профиля Species ⚡️ 🌘 🌍

Species ⚡️ 🌘 🌍1 год назад

How do you make video like this? Shareable?

Фото профиля Victoria Slocum

Victoria Slocum1 год назад

Green screen, Adobe Premiere, and lots of failed attempts and practice 😅

Фото профиля Flavio Milazzo, MSc

Flavio Milazzo, MSc1 год назад

Great share, thank you.

Похожие видео

Matryoshka dolls 🪆 = the key to AI efficiency. Gemini Embedding 2 leverages Matryoshka Representation Learning (MRL) so you can: 🔹 Dynamically truncate vectors for high-speed candidate matching without losing precision 🔹Slash database costs by choosing a smaller storage footprint without re-indexing 🔹 Adapt to any latency budget or accuracy requirement 📈💸 Learn how this helps build more efficient RAG, semantic search, and more:

Matryoshka dolls 🪆 = the key to AI efficiency. Gemini Embedding 2 leverages Matryoshka Representation Learning (MRL) so you can: 🔹 Dynamically truncate vectors for high-speed candidate matching without losing precision 🔹Slash database costs by choosing a smaller storage footprint without re-indexing 🔹 Adapt to any latency budget or accuracy requirement 📈💸 Learn how this helps build more efficient RAG, semantic search, and more:

Google for Developers

10,746 просмотров • 2 месяцев назад

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 просмотров • 10 месяцев назад

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

38,334 просмотров • 28 дней назад

$TAO is tackling the core challenges in machine learning, from optimizing data collection to faster inference, aiming to outperform giants like OpenAI and Microsoft. With a focus on computational efficiency and robust models, the race is on.

$TAO is tackling the core challenges in machine learning, from optimizing data collection to faster inference, aiming to outperform giants like OpenAI and Microsoft. With a focus on computational efficiency and robust models, the race is on.

Grayscale

88,595 просмотров • 1 год назад

A new Super Agent builder arrived at Genspark along with a Super Agent store. It allows users to automate their recurrent workflows for content creation, data management and more! The underlying system will automatically configure the agent architecture, select optimal models, and fine-tune its capabilities.

A new Super Agent builder arrived at Genspark along with a Super Agent store. It allows users to automate their recurrent workflows for content creation, data management and more! The underlying system will automatically configure the agent architecture, select optimal models, and fine-tune its capabilities.

TestingCatalog News 🗞

42,650 просмотров • 8 месяцев назад

Today we’re releasing V-JEPA, a method for teaching machines to understand and model the physical world by watching videos. This work is another important step towards Yann LeCun’s outlined vision of AI models that use a learned understanding of the world to plan, reason and accomplish complex tasks. Details ➡️ We're releasing a collection of V-JEPA vision models trained with a feature prediction objective using self-supervised learning. The models are able to understand and predict what is going on in a video, even with limited information. It learns by predicting missing or obscured parts of a video in its internal feature space. Unlike generative approaches that fill in missing pixels, this flexible approach enables up to 6x improvements in training and sample efficiency. The models were pre-trained on entirely unlabeled data, and a small amount of labeled data can be used to train a task-specific prediction head on top after pre-training. Our results show that, using a frozen backbone, our top V-JEPA models achieve 82.0% on Kinetics-400, 72.2% on Something-Something-v2 and 77.9% on ImageNet1K — competitive with or exceeding previous leading video models. We believe that this work is an important milestone on the path to advancing machine intelligence.

Today we’re releasing V-JEPA, a method for teaching machines to understand and model the physical world by watching videos. This work is another important step towards Yann LeCun’s outlined vision of AI models that use a learned understanding of the world to plan, reason and accomplish complex tasks. Details ➡️ We're releasing a collection of V-JEPA vision models trained with a feature prediction objective using self-supervised learning. The models are able to understand and predict what is going on in a video, even with limited information. It learns by predicting missing or obscured parts of a video in its internal feature space. Unlike generative approaches that fill in missing pixels, this flexible approach enables up to 6x improvements in training and sample efficiency. The models were pre-trained on entirely unlabeled data, and a small amount of labeled data can be used to train a task-specific prediction head on top after pre-training. Our results show that, using a frozen backbone, our top V-JEPA models achieve 82.0% on Kinetics-400, 72.2% on Something-Something-v2 and 77.9% on ImageNet1K — competitive with or exceeding previous leading video models. We believe that this work is an important milestone on the path to advancing machine intelligence.

AI at Meta

703,647 просмотров • 2 лет назад

#BlackHistoryMonth is a reminder to keep learning, to honour and amplify the voices of Black Canadians, and to celebrate their contributions to this country. It’s also a reminder to continue working together to build a more just Canada for all.

#BlackHistoryMonth is a reminder to keep learning, to honour and amplify the voices of Black Canadians, and to celebrate their contributions to this country. It’s also a reminder to continue working together to build a more just Canada for all.

Prime Minister of Canada

22,132 просмотров • 4 месяцев назад

New short course: Prompt Engineering with Llama 2, built in collaboration with Meta AI at Meta, and taught by Amit Sangani! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you please, and work alongside the global community advancing open models. Llama isn't a single model, it's a collection of models. In this course, you'll: - Learn the differences between different Llama 2 flavors, and when to use each. - Prompt the Llama chat models -- you'll also see how Llama's instruction tags work -- so they can help you with day-to-day tasks, like writing or summarization. - Use advanced prompting, like few-shot prompting for classification, and chain-of-thought prompting for solving logic problems. - Use specialized models in the Llama collection for specific tasks, like Code Llama to help you write, analyze, and improve code, and Llama Guard, which checks prompts and model responses for harmful content. The course also touches on how to run Llama 2 locally on your own computer. I hope you’ll take this course and try out these powerful, open models!

New short course: Prompt Engineering with Llama 2, built in collaboration with Meta AI at Meta, and taught by Amit Sangani! Meta's Llama 2 has been game-changing for AI. Building with open source lets you control your own data, scrutinize errors, update (or not) the models as you please, and work alongside the global community advancing open models. Llama isn't a single model, it's a collection of models. In this course, you'll: - Learn the differences between different Llama 2 flavors, and when to use each. - Prompt the Llama chat models -- you'll also see how Llama's instruction tags work -- so they can help you with day-to-day tasks, like writing or summarization. - Use advanced prompting, like few-shot prompting for classification, and chain-of-thought prompting for solving logic problems. - Use specialized models in the Llama collection for specific tasks, like Code Llama to help you write, analyze, and improve code, and Llama Guard, which checks prompts and model responses for harmful content. The course also touches on how to run Llama 2 locally on your own computer. I hope you’ll take this course and try out these powerful, open models!

Andrew Ng

162,798 просмотров • 2 лет назад

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

Andrew Ng

104,371 просмотров • 2 лет назад

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

AI at Meta

74,531 просмотров • 1 год назад

(a little late but) Happy 1 year to H4R !!! 🩷 It’s been so much fun creating so many memories and experiencing things with you guys. Thank you for all the love & support, always. Quite literally could nit do this without you guys✨ Love y’all and i’m super excited to see what this next year has in store for me/us! It’s only up

(a little late but) Happy 1 year to H4R !!! 🩷 It’s been so much fun creating so many memories and experiencing things with you guys. Thank you for all the love & support, always. Quite literally could nit do this without you guys✨ Love y’all and i’m super excited to see what this next year has in store for me/us! It’s only up

ryah 💕

50,209 просмотров • 2 месяцев назад

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)

Avthar

34,261 просмотров • 1 год назад

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Sakana AI

179,276 просмотров • 1 год назад

New PNAS paper. Historical GDP per capita data is scarce, but data on the places of birth, death, and occupations of famous individuals is abundant. In this paper we estimate the historical GDP per capita of hundreds of regions in Europe and North America using a machine learning model that leveraged data on about 500k famous biographies. Our estimates more-or-less quadruple the availability of historical GDP per capita estimates for the last 700 years. So why use biographies to augment historical GDP per capita data? Biographical data contains information about people who might have contributed directly to economic growth, like James Watt, or that were attracted to wealthy places looking for patrons, like Michelangelo. So we--mainly Philipp (Philipp Koch)--used this data to construct hundreds of features describing each European region. Then, we trained a machine learning model to find the features that explained most of the variance in a cross-validation test, where we split regions multiple times into a training set and a test set. On average, the model explained about 90% of the variance in GDP per capita of the regions it had not seen during training. But we wanted to go further, and Philipp really went to town by looking at different ways to validate our estimates. We found our estimates correlate positively with historical measures of wellbeing, church building activity, urbanization, and body height. We also used these measures to reproduce the basic Atlantic trade result of Acemoglu, Johnson, and Robison and to explore the economic consequences of the famous Lisbon earthquake of 1755. But what I personally loved most about this project, other than working with Philipp Koch and V, is that it shows that we can use machine learning methods not only to explore the future, but the past. There is a bright and growing future in the use of machine learning for economic history. Hope you enjoy the paper and the data. You can find links to the paper and a data exploration tool in the first comment.

New PNAS paper. Historical GDP per capita data is scarce, but data on the places of birth, death, and occupations of famous individuals is abundant. In this paper we estimate the historical GDP per capita of hundreds of regions in Europe and North America using a machine learning model that leveraged data on about 500k famous biographies. Our estimates more-or-less quadruple the availability of historical GDP per capita estimates for the last 700 years. So why use biographies to augment historical GDP per capita data? Biographical data contains information about people who might have contributed directly to economic growth, like James Watt, or that were attracted to wealthy places looking for patrons, like Michelangelo. So we--mainly Philipp (Philipp Koch)--used this data to construct hundreds of features describing each European region. Then, we trained a machine learning model to find the features that explained most of the variance in a cross-validation test, where we split regions multiple times into a training set and a test set. On average, the model explained about 90% of the variance in GDP per capita of the regions it had not seen during training. But we wanted to go further, and Philipp really went to town by looking at different ways to validate our estimates. We found our estimates correlate positively with historical measures of wellbeing, church building activity, urbanization, and body height. We also used these measures to reproduce the basic Atlantic trade result of Acemoglu, Johnson, and Robison and to explore the economic consequences of the famous Lisbon earthquake of 1755. But what I personally loved most about this project, other than working with Philipp Koch and V, is that it shows that we can use machine learning methods not only to explore the future, but the past. There is a bright and growing future in the use of machine learning for economic history. Hope you enjoy the paper and the data. You can find links to the paper and a data exploration tool in the first comment.

César A. Hidalgo

54,332 просмотров • 1 год назад

Lebron didn't only want team up with Wade And Bosh, he also wanted to team up with Carmelo Anthony and Also wanted to have a Super Bench And tried to blame the Bench players for losing in 2011 to the Mavericks SMH This is one of the reasons hes NOT The GOAT Imagine being this pathetic and needing this much help 😭😭

Lebron didn't only want team up with Wade And Bosh, he also wanted to team up with Carmelo Anthony and Also wanted to have a Super Bench And tried to blame the Bench players for losing in 2011 to the Mavericks SMH This is one of the reasons hes NOT The GOAT Imagine being this pathetic and needing this much help 😭😭

TheTruth

50,589 просмотров • 12 дней назад

All the best coaching in the world at the youngest ages is rendered useless if a child hasn’t developed the ability to focus their attention. You can bring the best coach in the world to your child’s training session and if they don’t pay full attention absolutely nothing takes place. Similar to inside a classroom where you can bring the teacher of the year to your child’s classroom and if they don’t focus and pay attention, learning does not take place. So it’s not always the case of good or bad coaching it’s often the case a child’s lack of ability to learn by not focusing on what is being taught. This is especially true for the youngest ages. This video is an example of a 5yr old child focusing their attention, trying to control an object with their feet, the ball. This becomes a mental task, married together with the action of movement, making it a physical task as well. The brain loves to learn while moving. Combining, mind and body, thinking and feeling, this allows the cerebellum, the seat of the unconscious mind, to create a chemical signature of this experience, which is emotions. Emotions are the on off switch for learning. Couple in a parent being present, this becomes a shared experience together, where the child is constantly seeking the parents approval, attention, and praise which creates a chemical electrical process in the body which is emotions. This facilitates, deep learning, and long-term memory, all disguised as playtime. A parent just being present allows for this experience to take place. A child this young rarely starts playing or exercising with a ball without someone being present. Being present and sharing this experience together is key for the learning process to take place. These movements are being stored in the non-declared memory which makes this implicit learning when you do something so many times it becomes natural and outside your conscious awareness. Like riding a bicycle or driving a car.

All the best coaching in the world at the youngest ages is rendered useless if a child hasn’t developed the ability to focus their attention. You can bring the best coach in the world to your child’s training session and if they don’t pay full attention absolutely nothing takes place. Similar to inside a classroom where you can bring the teacher of the year to your child’s classroom and if they don’t focus and pay attention, learning does not take place. So it’s not always the case of good or bad coaching it’s often the case a child’s lack of ability to learn by not focusing on what is being taught. This is especially true for the youngest ages. This video is an example of a 5yr old child focusing their attention, trying to control an object with their feet, the ball. This becomes a mental task, married together with the action of movement, making it a physical task as well. The brain loves to learn while moving. Combining, mind and body, thinking and feeling, this allows the cerebellum, the seat of the unconscious mind, to create a chemical signature of this experience, which is emotions. Emotions are the on off switch for learning. Couple in a parent being present, this becomes a shared experience together, where the child is constantly seeking the parents approval, attention, and praise which creates a chemical electrical process in the body which is emotions. This facilitates, deep learning, and long-term memory, all disguised as playtime. A parent just being present allows for this experience to take place. A child this young rarely starts playing or exercising with a ball without someone being present. Being present and sharing this experience together is key for the learning process to take place. These movements are being stored in the non-declared memory which makes this implicit learning when you do something so many times it becomes natural and outside your conscious awareness. Like riding a bicycle or driving a car.

Tom Byerトム•バイヤー

26,691 просмотров • 2 лет назад

Watch "Endless experimentation: Building AI models in the wild." This is a 50-minute, MIT lecture about problems when deploying models and LLMs in the real world and how to prepare to solve them. This is a great lecture for those building production machine learning.

Watch "Endless experimentation: Building AI models in the wild." This is a 50-minute, MIT lecture about problems when deploying models and LLMs in the real world and how to prepare to solve them. This is a great lecture for those building production machine learning.

Santiago

117,204 просмотров • 2 лет назад

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 просмотров • 7 месяцев назад