8/ For the curious, here are the achievements success rate on craftax across training, training for 1e9 steps (left) and training for 4e9 steps (right).

6/ Potential next steps could be to test it on Xland-Minigrid
, to test it on an Open-Ended meta-RL environment github.com/dunnolab/xla...
I'm also curious to implement Muesli (arxiv.org/abs/2104.06159) with transformerXL as in arxiv.org/abs/2301.07608

2/ We implement TransformerXL-PPO following "Stabilizing Transformers for Reinforcement
Learning" arxiv.org/abs/1910.06764
The code follows the template from PureJaxRL github.com/luchris429/p...
⚡️Training is fast thanks to JAX

1/⚡️Looking for a fast and simple Transformer baseline for your RL environment in JAX ?
Sharing my implementation of transformerXL-PPO: github.com/Reytuag/tran...
The implementation is the first to attain the 3rd floor and obtain advanced achievements in the challenging Craftax

This tweet appeared under this Techmeme headline:

Niels Rogge / @nielsrogge:

Interesting, the CEO of @Kimi_Moonshot was the first author of XLNet and TransformerXL Both of which were among the first models added to the @huggingface Transformers library in 2019 [image]

Full PyTorch Implementation of Transformer-XL

Explore the code and start building:
www.k-a.in/pyt-transfor...

#TransformerXL #PyTorch #DeepLearning #NLP #LanguageModeling #AI #MachineLearning #OpenSource #ResearchTools