Discover yuanmingqi/HAIRL Open Source project by Yuanmo (@yuanmingqi)

Stars
1
Language
Python
License
MIT License
Created almost 4 years ago
Updated over 3 years ago

yuanmingqi

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

Hybrid adversarial inverse reinforcement learning (HAIRL) is a model-free, one-stage, GA fashion and curiosity-driven beyond-demonstrator inverse reinforcement learning (IRL) algorithm.

rl-exploration-baselines

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).

Python

283

YOLOv3

The implementation of YOLOv3 based on TensorFlow 2.x and TensorFlow Lite

Python

UniNet

Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features

Python

ConvolutionBox

ConvolutionBox is a convenient tool for convolution visualization, which can help you with experiments!

JavaScript

pySavjeeCoin

Python implementation of the SavjeeCoin

Python

RISE

Rényi State Entropy for Accelerating Exploration in Reinforcement Learning

Python

Convolutional-Pose-Machines

The implementation of Convolutional Pose Machines based on TensorFlow 2.0 and TensorFlow Lite

Makefile

TibetanMNIST

A dataset of TibetanMNIST

YuanRL

Implementations of the Single-Agent Reinforcement Learning (SARL) and Multi-Agent Reinforcement Learning (MARL) algorithms.

Python

yuanmingqi/HAIRL

yuanmingqi

Reviews

Repository Details

More Repositories