iris
bet
iris | bet | |
---|---|---|
8 | 3 | |
757 | 93 | |
- | - | |
1.9 | 2.1 | |
3 months ago | 12 months ago | |
Python | Python | |
GNU General Public License v3.0 only | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
iris
-
From Deep to Long Learning
Yea, after all these LLMs are predicting one sequence of tokens from another sequence of tokens and the tokens could be anything, it just "happens" that text has the most knowledge and the easiest to input, then there are image, sound, video, but tokens could also be learned from world experience in RL:
Transformers are Sample-Efficient World Models:
https://github.com/eloialonso/iris#transformers-are-sample-e...
- What is the next booming topic in Deep RL?
-
Most Popular AI Research Sept 2022 - Ranked Based On Total GitHub Stars
Transformers are Sample Efficient World Models https://github.com/eloialonso/iris https://arxiv.org/abs/2209.00588v1
- [D] Most Popular AI Research Sept 2022 - Ranked Based On GitHub Stars
-
Minimal PyTorch re-implementation of GPT
This is actually a pretty neat, self-contained implementation that can super easily extended beyond stereotypical natural language models, for example to create world models for video games [1] or to create robot models that can learn to imitate from large, chaotic human demonstration data [2] (disclaimer, I'm an author on the second one.) Basically, GPT (or minGPT) models are EXCELLENT sequence modelers, almost to the point where you can throw any sensible sequence data at it and hope to get interesting results, as long as you don't overfit.
Even though I have only been working on machine learning for around six years, it's crazy to see how the landscape has changed so fast so recently, including diffusion models and transformers. It's not too much to say that we might expect more major breakthroughs by the end of this decade, and end in a place we can't even imagine right now!
[1] https://github.com/eloialonso/iris
- Transformers are Sample Efficient World Models
- [R] Transformers are Sample Efficient World Models: With the equivalent of only two hours of gameplay in the Atari 100k benchmark, IRIS outperforms humans on 10 out of 26 games and surpasses MuZero.
bet
-
Dobb·E: An open-source framework for learning household robotic manipulation
Indeed! In fact, I have a project [0] from last year that uses a GPT-style transformer to address that exact issue :) However, it’s hard to go far outside simulations in real home robotics without a good platform, out of which efforts came Dobb-E.
[0] https://mahis.life/bet/
- Minimal PyTorch re-implementation of GPT
-
Show HN: We trained a (mini) GPT for multi-modal robot behaviors
Hi HN!
First author of the paper here, thought some of you may enjoy reading about this! Even now, training robots on human demonstration data is the best way to get them to do new and exciting things in the real world. However, this generally requires a lot of data curation in the standard way: the robots can only follow along if you give them data that is solving a single task in a single way.
To improve the status quo, we introduce Behavior Transformer in this paper, which can learn from unlabeled demonstration data solving multiple different tasks in different ways using a GPT-like generator model. We had to make some modifications to fit the continuous actions, unlike the standard GPT model which fits discrete words.
As it turns out, unconditional rollouts from this model shows a lot more "natural" behavior (i.e. different tasks solved in different rollouts in different ways)_than standard behavioral cloning. More importantly, behavior transformers show much better mode coverage compared to previous models, and show some level of compositionality. Check out our videos! [1]
Finally, another oft-ignored part I am quite proud of is our code release -- we worked quite hard to make sure our code [2] is easy to read, reproduce, and remix! And also, did I tell you that these models train super fast? The Franka Kitchen environment in the top video [3] takes just 10 minutes on an Nvidia 3080 to the point you are seeing in the video. Compare that with standard RL training, and you might agree with me that a small number of demonstrations can truly go a long way!
Happy to answer questions, as well! Have a great Friday, wherever you are :)
[1] https://mahis.life/bet
[2] https://github.com/notmahi/bet
[3] https://mahis.life/bet/more/kitchen/
What are some alternatives?
setfit - Efficient few-shot learning with Sentence Transformers
Text2Light - [SIGGRAPH Asia 2022] Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
block-recurrent-transformer-pytorch - Implementation of Block Recurrent Transformer - Pytorch
machine-learning-articles - 🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
motion-diffusion-model - The official PyTorch implementation of the paper "Human Motion Diffusion Model"
CSL - [COLING 2022] CSL: A Large-scale Chinese Scientific Literature Dataset 中文科学文献数据集
VToonify - [SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer
storydalle
minGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
rliable - [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
git-re-basin - Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"