dhruvramani/Transformers-RL dhruvramani/Transformers-RL

  • Stars
    star
    155
  • Rank 235,816 (Top 5 %)
  • Language
    Python
  • License
    MIT License
  • Created over 3 years ago
  • Updated over 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
dhruvramani/Transformers-RL
github

dhruvramani

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

An easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"

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.

More Repositories

1

Terminal-on-FB-Messenger

Allows user to take full control of the terminal of their computer through Facebook's messaging service.
Python
411
star
2

C2AE-Multilabel-Classification

Tensorflow implementation for the paper 'Learning Deep Latent Spaces for Multi-Label Classfications' in AAAI 2017
Python
98
star
3

Neural-Architecture-Search-with-RL

Minimal Tensorflow implementation of the paper "Neural Architecture Search With Reinforcement Learning" presented at ICLR 2017
Python
42
star
4

gym-render-browser

Render RL environments on a web browser with just one extra line of code.
Python
19
star
5

model-based-atari

An easy to understand implementation of the paper "Model-Based Reinforcement Learning for Atari"
Python
13
star
6

keras2pytorch

Covert Keras models to Pytorch
Python
11
star
7

data-driven-robotics

A boilerplate (dbs, envs, teleop, models, web-apps) for robotic learning experiments & a Pytorch Implementation of "Learning Latent Plans from Play".
Python
9
star
8

Multilabel-Classification-Datasets

A collection of dataset blobs for multi label classification
Python
8
star
9

SORB

Experiment friendly non-ipython notebook version of "Search on the Replay Buffer"
Python
5
star
10

tf.attention

Plug-and-Play version of Attention implemented in Tensorflow
Python
2
star
11

SparseNet

A scikit-learn based implementation of Sparse-Net.
Python
2
star
12

Github-Repo-Getter

A simple script to get all the repositories of a Github User
Python
1
star
13

CarGame.cpp

A simple car game built in C++(98) as a high school project.
C++
1
star
14

DSA-NITW

AVOID AVOID AVOID!
C++
1
star
15

OffensEval

Python
1
star
16

rl-safety-imagination

Python
1
star
17

keras-alexnet

Python
1
star
18

image-caption

Python
1
star
19

Almabase-deduper

A web interface to identify duplicate data in your csv file using ML
Python
1
star
20

Parsed-V8-Node-Memory-Profiler

Parsed output for the V8-Node memory bindings
JavaScript
1
star