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。

This is hugeeee for open-source RL environments. You can now discover environments across OpenEnv, Verifiers, Harbor, NeMo Gym, and more, all on the Hugging Face Hub. A common home for RL environments is long overdue. Excited for what’s coming next !

Adithya S K

16,301 subscribers

16,350 次观看 • 9 天前 •via X (Twitter)

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

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Adithya S K

47,002 次观看 • 5 个月前

🤿 ICYMI: Agents don’t learn in the abstract — they learn by interacting with environments. This post on RL environments is more relevant than ever as agents move into production and evaluation gets harder.

🤿 ICYMI: Agents don’t learn in the abstract — they learn by interacting with environments. This post on RL environments is more relevant than ever as agents move into production and evaluation gets harder.

Snorkel AI

1,694,092 次观看 • 10 个月前

🚨Current scalable RL algos train a policy w/o value func, which is limiting with learning in open-ended, non-stationary, dynamic environments. But, how to scale value-based RL with more data/compute is unclear... Not anymore: presenting scaling laws for value-based RL 🧵⬇️

🚨Current scalable RL algos train a policy w/o value func, which is limiting with learning in open-ended, non-stationary, dynamic environments. But, how to scale value-based RL with more data/compute is unclear... Not anymore: presenting scaling laws for value-based RL 🧵⬇️

Aviral Kumar

37,401 次观看 • 1 年前

🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇

🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇

Marco Mascorro

19,448 次观看 • 7 个月前

Some personal news: I recently joined Cursor. Cursor is a small, ambitious team, and they’ve created my favorite AI systems. We’re now building frontier RL models at scale in real-world coding environments. Excited for how good coding is going to be.

Some personal news: I recently joined Cursor. Cursor is a small, ambitious team, and they’ve created my favorite AI systems. We’re now building frontier RL models at scale in real-world coding environments. Excited for how good coding is going to be.

Sasha Rush

336,345 次观看 • 1 年前

The next wave of AI innovation is already here. Are you ready for it? Nesa’s privacy guarantees are enabling broader applications of AI across both enterprise and consumer environments. Energy solutions, biotech, predictive analytics, robotics, all of it is happening right now on the Playground. There’s still time to position yourself early. Join the waitlist today 👉

The next wave of AI innovation is already here. Are you ready for it? Nesa’s privacy guarantees are enabling broader applications of AI across both enterprise and consumer environments. Energy solutions, biotech, predictive analytics, robotics, all of it is happening right now on the Playground. There’s still time to position yourself early. Join the waitlist today 👉

Nesa

13,155 次观看 • 8 个月前

The day has finally arrived! 🎉 “What’s Next” is now available, and I couldn’t be more excited! It’s been a long journey, and I can’t wait to hear your thoughts on it. You can get “What’s Next” wherever you purchase your books. Thank you for your support, and happy reading! 📚

The day has finally arrived! 🎉 “What’s Next” is now available, and I couldn’t be more excited! It’s been a long journey, and I can’t wait to hear your thoughts on it. You can get “What’s Next” wherever you purchase your books. Thank you for your support, and happy reading! 📚

(((Melissa Fitzgerald)))

202,450 次观看 • 2 年前

SISU GTT Is a high-performance multi-purpose platform intended for all geographical environments, including extreme climate conditions and the harshest terrains. #mobility #protection #design #sisuauto #sisugtt

SISU GTT Is a high-performance multi-purpose platform intended for all geographical environments, including extreme climate conditions and the harshest terrains. #mobility #protection #design #sisuauto #sisugtt

Oy Sisu Auto Ab

23,442 次观看 • 15 天前

This is Ray3.14 with Modify (Video-to-Video). Now with native 1080p and improved visual stability for motion transfer. Better frame-to-frame coherence for styles, characters, and environments, producing stronger animation and more polished results. Available now in Dream Machine.

This is Ray3.14 with Modify (Video-to-Video). Now with native 1080p and improved visual stability for motion transfer. Better frame-to-frame coherence for styles, characters, and environments, producing stronger animation and more polished results. Available now in Dream Machine.

Luma

25,792 次观看 • 8 个月前

ARC-AGI-3 is out now! We've designed the benchmark to evaluate agentic intelligence via interactive reasoning environments. Beating ARC-AGI-3 will be achieved when an AI system matches or exceeds human-level action efficiency on all environments, upon seeing them for the first time. We've done extensive human testing that shows 100% of these environments are solvable by humans, upon first contact, with no prior training and no instructions. Meanwhile, all frontier AI reasoning models do under 1% at this time.

ARC-AGI-3 is out now! We've designed the benchmark to evaluate agentic intelligence via interactive reasoning environments. Beating ARC-AGI-3 will be achieved when an AI system matches or exceeds human-level action efficiency on all environments, upon seeing them for the first time. We've done extensive human testing that shows 100% of these environments are solvable by humans, upon first contact, with no prior training and no instructions. Meanwhile, all frontier AI reasoning models do under 1% at this time.

François Chollet

625,848 次观看 • 6 个月前

Today we’re announcing a new open-source SOTA for AI drone autonomy SOTApilot hit 95.34% success on Swarm — our public, 1,000-seed benchmark for general UAV navigation across 6 procedural environments GitHub in the first reply 👇 400+ submissions 25 top-model improvements 2 months Our challenge for the next 3 months: make Swarm the benchmark the world uses to measure AI drone autonomy SOTApilot begins now 🐝

Today we’re announcing a new open-source SOTA for AI drone autonomy SOTApilot hit 95.34% success on Swarm — our public, 1,000-seed benchmark for general UAV navigation across 6 procedural environments GitHub in the first reply 👇 400+ submissions 25 top-model improvements 2 months Our challenge for the next 3 months: make Swarm the benchmark the world uses to measure AI drone autonomy SOTApilot begins now 🐝

Swarm

31,577 次观看 • 4 个月前

You can now do RL weight sync over HF Buckets. > Async GRPO + LoRA in TRL > train on one Job, serve vLLM on others > sync just the small delta adapter through a Bucket. Trainer, inference and storage, all on Hugging Face infra. Beautifully optimised loop by @DirhoussssiAmine 👇 3h27 → 53 min for the same reward.

You can now do RL weight sync over HF Buckets. > Async GRPO + LoRA in TRL > train on one Job, serve vLLM on others > sync just the small delta adapter through a Bucket. Trainer, inference and storage, all on Hugging Face infra. Beautifully optimised loop by @DirhoussssiAmine 👇 3h27 → 53 min for the same reward.

Adithya S K

18,551 次观看 • 26 天前

This atmosphere is absurd. The kids who are “D-I or bust” are missing out. Go somewhere you can compete for national titles and play in environments like this: NCAA Division II Minn. St. Athletics Northwest Athletics

This atmosphere is absurd. The kids who are “D-I or bust” are missing out. Go somewhere you can compete for national titles and play in environments like this: NCAA Division II Minn. St. Athletics Northwest Athletics

Andy Peterson

86,943 次观看 • 2 年前

My next album SUBSTANCE is coming this year A story narrated by EV A lot more info coming soon, can’t wait for you all to hear this 🌹 But for now you can pre-save the next single off the album via link in my bio on insta

My next album SUBSTANCE is coming this year A story narrated by EV A lot more info coming soon, can’t wait for you all to hear this 🌹 But for now you can pre-save the next single off the album via link in my bio on insta

MPH

11,077 次观看 • 1 年前

INSANE...this is an Open Source Video model available for free on Hugging Face. LongCat just dropped an amazing video avatar model that can do crazy things. And it's 100% Opensource.

Shubham Saboo

30,601 次观看 • 4 个月前

Robot Utility Models (RUMs) enable basic tasks – door opening, drawer opening, object reorientation, etc. – at ~90% accuracy without ANY finetuning (i.e. zero-shot) in unseen new environments. Fully open source!!! models, data, code & hw. We think this is super exciting, why?👇 1. Unlocks many practical home utility tasks that often involve these basic tasks as part of an action chain. “Go get me a fork” involves opening the kitchen door and then opening the cutlery drawer. 2. This works well **zero-shot in unseen and new** environments, which is practically a huge deal. Turn the robot on, and get going. 3. The recipe for building a new model is fairly generic, and we think with a bit more refinement this can be a general recipe to build many more Utility models. More details and access 👇

Robot Utility Models (RUMs) enable basic tasks – door opening, drawer opening, object reorientation, etc. – at ~90% accuracy without ANY finetuning (i.e. zero-shot) in unseen new environments. Fully open source!!! models, data, code & hw. We think this is super exciting, why?👇 1. Unlocks many practical home utility tasks that often involve these basic tasks as part of an action chain. “Go get me a fork” involves opening the kitchen door and then opening the cutlery drawer. 2. This works well zero-shot in unseen and new environments, which is practically a huge deal. Turn the robot on, and get going. 3. The recipe for building a new model is fairly generic, and we think with a bit more refinement this can be a general recipe to build many more Utility models. More details and access 👇

Mahi Shafiullah 🏠🤖

89,671 次观看 • 2 年前

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵

Decart

415,240 次观看 • 1 年前