All Projects → dhruvramani → Transformers-RL

dhruvramani / Transformers-RL

Licence: MIT license
An easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Transformers-RL

Transformer Tts
A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
Stars: ✭ 418 (+290.65%)
Mutual labels:  transformer, attention-mechanism
Se3 Transformer Pytorch
Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. This specific repository is geared towards integration with eventual Alphafold2 replication.
Stars: ✭ 73 (-31.78%)
Mutual labels:  transformer, attention-mechanism
Nmt Keras
Neural Machine Translation with Keras
Stars: ✭ 501 (+368.22%)
Mutual labels:  transformer, attention-mechanism
Transformer
A TensorFlow Implementation of the Transformer: Attention Is All You Need
Stars: ✭ 3,646 (+3307.48%)
Mutual labels:  transformer, attention-mechanism
Routing Transformer
Fully featured implementation of Routing Transformer
Stars: ✭ 149 (+39.25%)
Mutual labels:  transformer, attention-mechanism
Neural sp
End-to-end ASR/LM implementation with PyTorch
Stars: ✭ 408 (+281.31%)
Mutual labels:  transformer, attention-mechanism
Sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+825.23%)
Mutual labels:  transformer, attention-mechanism
Transformer-in-Transformer
An Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
Stars: ✭ 40 (-62.62%)
Mutual labels:  transformer, attention-mechanism
Transformer In Generating Dialogue
An Implementation of 'Attention is all you need' with Chinese Corpus
Stars: ✭ 121 (+13.08%)
Mutual labels:  transformer, attention-mechanism
Overlappredator
[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
Stars: ✭ 106 (-0.93%)
Mutual labels:  transformer, attention-mechanism
galerkin-transformer
[NeurIPS 2021] Galerkin Transformer: a linear attention without softmax
Stars: ✭ 111 (+3.74%)
Mutual labels:  transformer, attention-mechanism
Linear Attention Transformer
Transformer based on a variant of attention that is linear complexity in respect to sequence length
Stars: ✭ 205 (+91.59%)
Mutual labels:  transformer, attention-mechanism
linformer
Implementation of Linformer for Pytorch
Stars: ✭ 119 (+11.21%)
Mutual labels:  transformer, attention-mechanism
Pytorch Original Transformer
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
Stars: ✭ 411 (+284.11%)
Mutual labels:  transformer, attention-mechanism
pynmt
a simple and complete pytorch implementation of neural machine translation system
Stars: ✭ 13 (-87.85%)
Mutual labels:  transformer, attention-mechanism
Awesome Bert Nlp
A curated list of NLP resources focused on BERT, attention mechanism, Transformer networks, and transfer learning.
Stars: ✭ 567 (+429.91%)
Mutual labels:  transformer, attention-mechanism
FragmentVC
Any-to-any voice conversion by end-to-end extracting and fusing fine-grained voice fragments with attention
Stars: ✭ 134 (+25.23%)
Mutual labels:  transformer, attention-mechanism
Image-Caption
Using LSTM or Transformer to solve Image Captioning in Pytorch
Stars: ✭ 36 (-66.36%)
Mutual labels:  transformer, attention-mechanism
Eqtransformer
EQTransformer, a python package for earthquake signal detection and phase picking using AI.
Stars: ✭ 95 (-11.21%)
Mutual labels:  transformer, attention-mechanism
Eeg Dl
A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Stars: ✭ 165 (+54.21%)
Mutual labels:  transformer, attention-mechanism

Transformers-RL

An easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning". I searched around a lot for an easy-to-understand implementation of transformers for RL but couldn't find it. Hence, had to get my hands dirty.

The stable TransformerXL (GTrXL block in the paper) and other layers are present in layers.py. To implement the TrXL-I block, set gating=False for StableTransformerEncoderLayerXL.

I implemented a basic gausian policy in policies.py. Additional policy implementations for different kind of action-spaces are welcome! Send a PR.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].