clear-nus/MuMMI
Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning
This project helps robotics engineers train intelligent systems that can learn complex tasks using data from multiple sensors, even when some sensors are unreliable or have missing information. It takes raw sensor readings from various sources (like cameras and depth sensors) and produces a robust 'world model' that the robot uses to make decisions. Robotics researchers and engineers developing self-supervised learning systems for robots would find this useful.
No commits in the last 6 months.
Use this if you need to train a robot to perform tasks using observations from multiple, potentially noisy or incomplete, sensory inputs.
Not ideal if your application involves single-sensor input or if you are looking for a pre-trained model rather than a training framework.
Stars
13
Forks
2
Language
Python
License
—
Category
Last pushed
Jun 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/clear-nus/MuMMI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
adambielski/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
Papers, code and datasets about deep learning and multi-modal learning for video analysis
KaiyangZhou/pytorch-vsumm-reinforce
Unsupervised video summarization with deep reinforcement learning (AAAI'18)