Stars
Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
A repo containing essential ROS2 (Humble) features for controlling Autonomous Mobile Robots (AMRs).
Open-Sora: Democratizing Efficient Video Production for All
Homework 4 for 2024 DRL module of NTHU.
A curated list of Decision Transformer resources (continually updated)
An OpenAI Gym environment for the Flappy Bird game
Code for the paper "Quantifying Transfer in Reinforcement Learning"
Docker image for Clearpath's Husky A200 on ROS 1 Melodic
[ICCV'23] Learning Vision-and-Language Navigation from YouTube Videos
Official implementation of learning to terminate in object navigation, accepted to ACML 2023.
Unofficial re-implementation of "Learning Latent Dynamics for Planning from Pixels" (https://arxiv.org/abs/1811.04551 ) with PyTorch
Code for training embodied agents using IL and RL finetuning at scale for ObjectNav
Code release for NeRF (Neural Radiance Fields)
Official Github repository for "Renderable Neural Radiance Map for Visual Navigation". (CVPR 2023)
Slam Gmapping for ROS2 with a map cleaning service.
Vision-and-Language Navigation in Continuous Environments using Habitat
Python implementation of the paper Learning hierarchical relationships for object-goal navigation
Reinforcement Deep Double Q-Learning implemented with Pytorch
Includes several attempts to use deep learning techniques to train the neural network to learn a grasp detection,
This project involves the approach to extract SIFT(Scale-Invariant Feature Transform) features from training data of given dataset with 5 different classes, and clustering the result SIFT descripto…
An pytorch implementation of Monte-Carlo Policy Gradient algorithm to address CartPole-v0 problem under Open-AI GYM environment.
Using deep learning to detect smiles from a live video feed.
Train and test Smile-Detector Machine Learning models / 利用机器学习模型训练和检测笑脸