superjeary Goto Github PK

softlearning

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

softqlearning

Reinforcement Learning with Deep Energy-Based Policies

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

spatial_softmax-pytorch

spirl

Official implementation of "Accelerating Reinforcement Learning with Learned Skill Priors", Pertsch et al., CoRL 2020

surreal

Open-Source Distributed Reinforcement Learning Framework by Stanford Vision and Learning Lab

tams_ur5_setup

TAMS' UR5 setup in the local laboratory

tensor2robot

Distributed machine learning infrastructure for large-scale robotics research

tidy-reinforcement-learning

Tensorflow implementation of reinforcement learning (PG, A2C, DQN, DDPG, PPO, HER, SAC).

time-in-state-rl

Sim2Real Transfer for Deep Reinforcement Learning with Stochastic State Transition Delays, CORL-2020.

train-robot-arm-from-scratch

Build environment and train a robot arm from scratch (Reinforcement Learning)

triad_openvr

This is an enhanced wrapper for the already excellent pyopenvr library by cmbruns. The goal of this library is to create easy to use python functions for any SteamVR tracked system.

turtlebot3_machine_learning

universal_robot

ROS-Industrial universal robot meta-package (http://wiki.ros.org/universal_robot)

uof-paper-code

Official implementation for the UOF paper (algorithm & environment)

ur-reinforcement-learning

For Reinforcement learning based on rlkit using UR5 and Robotiq grepper on ROS(Robot Operating System)

ur-robotiq-85-helab

ur5-with-robotiq-gripper-and-kinect

This package enables an UR5 arm with a Robotiq 85 Gripper to be used with ros_control and MoveIt!. A Microsoft Kinect is used to create an Octomap.

ur5_robotiq85_moveit

UR5_Robotiq85_Moveit ROS Kinetic

ur5_ros-gazebo

Universal Robot (UR5) Pick and Place Simulation in ROS-Gazebo with a USB Cam and Vacuum Grippers

ur5_sim

Gazebo simulation of a UR5 with gripper, etc.

ur_gym

A reinforcement learning ready gazebo environment with Universal Robot 10. Similar to gym API.

ur_modern_driver

The new driver for the UR3/UR5/UR10 robot arms from universal robots

ur_moveit_planner

moveit planner for universal robot ur5

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

ur_ws

Universal robot with robotiq hand workspace

vision_based_cartpole_dqn

Implementation of the CartPole from OpenAI's Gym using only visual input for Reinforcement Learning control with DQN

visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

vive_ik_demo

A full body tracking demo using HTC Vive and Trackers