superjeary's repositories
multi_robots
通过键盘输入在gazebo中分别控制多个UR5机器人
project-RL-D4PG-continuous-control
Implementing a D4PG agent for an env. similar to Unity's Reacher env.
surreal
Open-Source Distributed Reinforcement Learning Framework by Stanford Vision and Learning Lab
visual-pushing-grasping
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
D4PG
Tensorflow implementation of a Deep Distributed Distributional Deterministic Policy Gradients (D4PG) network, trained on OpenAI Gym environments.
bullet3
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Arnold
Arnold - DOOM Agent
CycleGAN-Keras
Keras implementation of CycleGAN using a tensorflow backend.
ur-reinforcement-learning
For Reinforcement learning based on rlkit using UR5 and Robotiq grepper on ROS(Robot Operating System)
UR_with_Robotiq_grasp_gazebo
A grasp simulation environment in gazebo: UR robot arm with a 85mm robotiq gripper that can be drived to grasp things through moveit
Solving-openAI-Gym-MountainCarProblem-using-DQN-with-Image-input
I have targeted to solve the benchmark problem in Reinforcement learning literature using Deep Q-networks with images as the only input to the model. Keras was used to model the Convolutional neural network which predicts the best action to take in a given state
d4pg-pytorch
PyTorch implementation of Distributed Distributional Deterministic Policy Gradients (https://arxiv.org/abs/1804.08617)
DDPG
End to End Mobile Robot Navigation using DDPG (Continuous Control with Deep Reinforcement Learning) based on Tensorflow + Gazebo
Hacking-SotA-UR5
UR5 Arm + RobotiQ 85 gripper - Pick and Place, Obstacle Avoidance
robotics-rl-srl
S-RL Toolbox: Reinforcement Learning (RL) and State Representation Learning (SRL) for Robotics
DDPG-Continuous-Control-1Reacher
This is the project where DDPG is employed for 2-DOF robot arm (reacher).
Vision_Based_CartPole_DQN
Implementation of the CartPole from OpenAI's Gym using only visual input for Reinforcement Learning control with DQN
tams_ur5_setup
TAMS' UR5 setup in the local laboratory
gym
A toolkit for developing and comparing reinforcement learning algorithms.
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
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.
Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
pytorch-CycleGAN-and-pix2pix
Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)
HIRO
The hierarchy reinforcement learning algorithm(based on DDPG)
Pix2Pix-Keras
基于pix2pix模型的动漫图片自动上色(keras实现) 2019-2-25
Siamese-Networks-for-One-Shot-Learning
Implementation of Siamese Neural Networks for One-shot Image Recognition
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.
Robotics-DDPG-HER
In this video, I use OpenAi Robotics environment Fetch to train a robot to lift, slide, move objectives to defined targets. I do this using Deep Deterministic Policy Gradients (DDPG) and Hindsight Experience Replay (HER) in RL to do this.