ShahRutav's repositories
PyTorch-VAE
A Collection of Variational Autoencoders (VAE) in PyTorch.
pytorch_sac
PyTorch implementation of Soft Actor-Critic (SAC)
agenthive
AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.
cuda-training-series
Training materials associated with NVIDIA's CUDA Training Series (www.olcf.ornl.gov/cuda-training-series/)
curl
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
dm_control
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
dmcontrol-generalization-benchmark
DMControl Generalization Benchmark
EMNLP-2021-Findings
This repo has the code for the paper "Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework" accepted at EMNLP 2021 Findings.
LIBERO
Benchmarking Knowledge Transfer in Lifelong Robot Learning
obj2mjcf
A CLI for processing composite Wavefront OBJ files into a MuJoCo-conducive format
object_sim
MuJoCo Models for general objects
peract
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation
pytorch-grad-cam
Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
r3m
Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data
RLBench
A large-scale benchmark and learning environment.
rlds_dataset_builder
An example RLDS dataset builder for X-embodiment dataset conversion.
robomimic
robomimic: A Modular Framework for Robot Learning from Demonstration
RRL-1
Code for RRL (https://sites.google.com/view/abstractions4rl)
torchrl_examples
Training examples using TorchRL repo
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
VIMA
Official Algorithm Implementation of Paper "VIMA: General Robot Manipulation with Multimodal Prompts"
VIMABench
Official Task Suite Implementation of Paper "VIMA: General Robot Manipulation with Multimodal Prompts"
YARR
Yet Another Robotics and Reinforcement (YARR) learning framework for PyTorch.