TianQi-777

Build_LK_OpticalFlow

The purpose of this demo is to better understand the underlying implementation of single level optical flow and multi level optical flow with forward or inverse.

Build_ORB_FeatureDescriptor

The purpose of this demo is to better understand the underlying implementation of ORB.

BundleAdjustmentWith_G-N

I write a simple Gaussian Newton method , and use Bundle Adjustment to optimize the pose.

DensePointCloudVisualization_Pangolin

This demo is a simple 3D reconstruction of the room with an RGB-D camera.I also provide KITTI's communication interface.

dsvo

Direct Stereo Visual Odometry

Eigen_MatrixSolution_QR_Cholesky

This is a small demo to learn Eigen library for QR,Cholesky and decomposition dynamic size matrix

Gaussian-NewtonMethodForCurveFittingExperiment

This demo is curve fitting by G-N method,and it can help us better understand the optimization process.

ORB-SLAM2_with_camera_or_video

This is a project modified on the basis of ORB-SLAM2 to use your own camera of PC or video.

TrajectoryDrawing

The trajectory of the robot is known and plotted with Pangolin.

TrajectoryErrorCalculationAndDrawing

This is a small demo to compare and plot SLAM estimated trajectories and ground-truth trajectories with RMSE and Pangolin..

TianQi-777/awesome-offline-rl

An index of algorithms for offline reinforcement learning (offline-rl)

TianQi-777/causalcity.github.io

TianQi-777/dcdi

Repository for "Differentiable Causal Discovery from Interventional Data"

TianQi-777/dcg

TianQi-777/deeprl_network

multi-agent deep reinforcement learning for networked system control.

TianQi-777/dreamer-pytorch

Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.

TianQi-777/dreamer-pytorch-1

pytorch-implementation of Dreamer (Model-based Image RL Algorithm)

TianQi-777/gym-minigrid

Minimalistic gridworld package for OpenAI Gym

TianQi-777/IC3Net

Code for ICLR 2019 paper: Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

TianQi-777/ICQ

Codes accompanying the paper "Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning" (NeurIPS 2021 Spotlight https://arxiv.org/abs/2106.03400)

TianQi-777/inference-based-messaging

Implementation of “Inference-based Deterministic Messaging For Multi-Agent Communication”.

TianQi-777/lab2d

A customisable 2D platform for agent-based AI research

TianQi-777/MOReL

Model-Based Offline Reinforcement Learning

TianQi-777/mpo

PyTorch Implementation of the Maximum a Posteriori Policy Optimisation

TianQi-777/multi-agent-neurosym-transformers

Neurosymbolic transformers for multi-agent communication.

TianQi-777/Multi-Agent-Reinforcement-Learning-Environment

Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

TianQi-777/MultiAgentPerception

Official source code to CVPR'20 paper, "When2com: Multi-Agent Perception via Communication Graph Grouping"

TianQi-777/OfflineRL

A collection of offline reinforcement learning algorithms. Codes are cloned from https://agit.ai/Polixir/OfflineRL

TianQi-777/on-policy

This is the official implementation of Multi-Agent PPO.

TianQi-777/PettingZoo

Gym for multi-agent reinforcement learning

TianQi-777/pymarl2

Rethinking the Importance of Implementation Tricks in Multi-Agent Reinforcement Learning

TianQi-777/pytorch_geometric

Geometric Deep Learning Extension Library for PyTorch

TianQi-777/qlib

Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies.

TianQi-777/RecBole

A unified, comprehensive and efficient recommendation library

TianQi-777/Reinforcement-learning

Modular implementations of reinforcement learning algorithms with PyTorch

TianQi-777/SMAC

StarCraft II Multi Agent Challenge : QMIX, COMA, LIIR, QTRAN, Central V, ROMA, RODE, DOP, Graph MIX

TianQi-777/sumo

Eclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians and comes with a large set of tools for scenario creation.

TianQi-777/TEDVAE

TianQi-777/TMC

Pytorch implementation of "Succinct and Robust Multi-Agent Communication With Temporal Message Control"

TianQi-777/xingtian

xingtian is a componentized library for the development and verification of reinforcement learning algorithms