iris
rliable
| iris | rliable | |
|---|---|---|
| 8 | 15 | |
| 756 | 702 | |
| - | 2.1% | |
| 1.9 | 2.5 | |
| 3 months ago | about 2 months ago | |
| Python | Jupyter Notebook | |
| GNU General Public License v3.0 only | Apache License 2.0 |
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.
rliable
-
[D] What is standard practice in RL when reporting average returns across multiple seeds in a table or a plot?
You can also look up https://github.com/google-research/rliable https://arxiv.org/pdf/2108.13264.pdf (Neurips 21 outstanding paper) IMHO the field would benefit if its moves in that direction.
-
What is the next booming topic in Deep RL?
You might like the best paper at NeurIPS last year: https://agarwl.github.io/rliable/
-
"Human-level Atari 200x faster", DeepMind 2022 (200x reduction in dataset scale required by Agent57 for human performance)
Deep RL at the Edge of the Statistical Precipice https://agarwl.github.io/rliable/
- How Hugging Face 🤗 can contribute to the Deep Reinforcement Learning Ecosystem?
-
Deep RL at the Edge of Statistical Precipice (NeurIPS Outstanding Paper)
You can find the paper, slides and poster at agarwl.github.io/rliable. The OP already put the poster here.
-
Google Highlights How Statistical Uncertainty Of Outcomes Must Be Considered To Evaluate Deep RL Reliably and Propose A Python Library Called ‘RLiable’
A recent Google study highlights how statistical uncertainty of outcomes must be considered for deep RL evaluation to be reliable, especially when only a few training runs are used. Google has also released an easy-to-use Python library called RLiable to help researchers incorporate these tools.
-
[R] Rliable: Better Evaluation for Reinforcement Learning—A Visual Explanation
Website: https://agarwl.github.io/rliable/
-
Towards creating better reward functions in a custom environment| Sensitivity analysis [Question]
First off, "performance" is highly speculative. So make sure you nail down what you mean and ensure reliability of those measurements. Check out https://github.com/google-research/rliable.
- Deep Reinforcement Learning at the Edge of the Statistical Precipice
-
Best RL papers from the past year or two?
Our NeurIPS'21 oral on Deep RL at the Edge of the Statistical Precipice would make for a fun read :)
What are some alternatives?
setfit - Efficient few-shot learning with Sentence Transformers
CARLA - CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Text2Light - [SIGGRAPH Asia 2022] Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
cleverhans - An adversarial example library for constructing attacks, building defenses, and benchmarking both
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
whisper - Robust Speech Recognition via Large-Scale Weak Supervision