superjeary Goto Github PK

deep-convolutional-autoencoder

This is a tutorial on creating a deep convolutional autoencoder with tensorflow.

deep-reinforcement-learning-algorithms-with-pytorch

PyTorch implementations of deep reinforcement learning algorithms and environments

deep-rl-keras

Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)

deeplearning_demo

深度学习入门的一些简单例子

deepmimic

Motion imitation with deep reinforcement learning.

dehrl

Diversity−Driven Extensible Hierarchical Reinforcement Learning. AAAI 2019.

dher

DHER: Hindsight Experience Replay for Dynamic Goals (ICLR-2019)

drqn

DRQN for navigating 3D environments

drqn-keras

Atari-DRQN (keras ver.)

ecanet

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

ecnu_ur5_setup

ur5 and robotiq 85 package

faceswap-gan

A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

facial-similarity-with-siamese-networks-in-pytorch

Implementing Siamese networks with a contrastive loss for similarity learning

fetchreach_gym

Implementation of DDPG+HER on gym robotics environment FetchReach-v1

flow_rl

ggcnn

Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)

good_robot

“Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

gym

A toolkit for developing and comparing reinforcement learning algorithms.

hacking-sota-ur5

UR5 Arm + RobotiQ 85 gripper - Pick and Place, Obstacle Avoidance

hierarchical_il_rl

Code for hierarchical imitation learning and reinforcement learning

hiro

The hierarchy reinforcement learning algorithm(based on DDPG)

imitation_from_observation

Learning to Imitate Behaviors from Raw Video via Context Translation

info8003-1-dqn-images

Project aiming to solve learn a car to drive up a hill using Reinforcement Learning. In this project, the inputs are the image only. The solution was found by creating a DQN with a few Conv. layers.

invite-robotics

Integration of Motoman CSDA10f dual arm robot with ROS, Moveit and Gazebo, with aims of creating a robotics developing platform for Invite GmbH, pre-configured to be simple to use and learn.

keras-rl

Deep Reinforcement Learning for Keras.

keras-semantic-segmentation

Keras-Semantic-Segmentation

kinova-ros

Official ROS packages for Kinova robotic arms

mask-attention_a3c

mil

Code for "One-Shot Visual Imitation Learning via Meta-Learning"

models

Models and examples built with TensorFlow