GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → kinwo → deeprl-continuous-control

kinwo / deeprl-continuous-control

Licence: other
Learning Continuous Control in Deep Reinforcement Learning

Programming Languages

HTML
75241 projects
python
139335 projects - #7 most used programming language
Jupyter Notebook
11667 projects

Labels

reinforcement-learningdeep-reinforcement-learningpytorchreinforcement-learning-algorithmsddpgcontinuous-controlddpg-algorithmddpg-agentunity-ml-agents

Projects that are alternatives of or similar to deeprl-continuous-control

Deep-rl-mxnet
Mxnet implementation of Deep Reinforcement Learning papers, such as DQN, PG, DDPG, PPO
Stars: ✭ 26 (+85.71%)
Mutual labels:  deep-reinforcement-learning, reinforcement-learning-algorithms, ddpg
LWDRLC
Lightweight deep RL Libraray for continuous control.
Stars: ✭ 14 (+0%)
Mutual labels:  deep-reinforcement-learning, ddpg, continuous-control
motion-planner-reinforcement-learning
End to end motion planner using Deep Deterministic Policy Gradient (DDPG) in gazebo
Stars: ✭ 99 (+607.14%)
Mutual labels:  deep-reinforcement-learning, ddpg, continuous-control
Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+28557.14%)
Mutual labels:  deep-reinforcement-learning, reinforcement-learning-algorithms, ddpg
Deep Reinforcement Learning Algorithms
31 projects in the framework of Deep Reinforcement Learning algorithms: Q-learning, DQN, PPO, DDPG, TD3, SAC, A2C and others. Each project is provided with a detailed training log.
Stars: ✭ 167 (+1092.86%)
Mutual labels:  deep-reinforcement-learning, ddpg
Minimalrl
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Stars: ✭ 2,051 (+14550%)
Mutual labels:  deep-reinforcement-learning, ddpg
Fruit-API
A Universal Deep Reinforcement Learning Framework
Stars: ✭ 61 (+335.71%)
Mutual labels:  deep-reinforcement-learning, reinforcement-learning-algorithms
Pytorch Drl
PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.
Stars: ✭ 233 (+1564.29%)
Mutual labels:  deep-reinforcement-learning, ddpg
Elegantrl
Lightweight, efficient and stable implementations of deep reinforcement learning algorithms using PyTorch.
Stars: ✭ 575 (+4007.14%)
Mutual labels:  deep-reinforcement-learning, ddpg
Pytorch A2c Ppo Acktr Gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Stars: ✭ 2,632 (+18700%)
Mutual labels:  deep-reinforcement-learning, continuous-control
yarll
Combining deep learning and reinforcement learning.
Stars: ✭ 84 (+500%)
Mutual labels:  deep-reinforcement-learning, reinforcement-learning-algorithms
Deep Reinforcement Learning In Large Discrete Action Spaces
Implementation of the algorithm in Python 3, TensorFlow and OpenAI Gym
Stars: ✭ 132 (+842.86%)
Mutual labels:  deep-reinforcement-learning, ddpg
Easy Rl
强化学习中文教程，在线阅读地址：https://datawhalechina.github.io/easy-rl/
Stars: ✭ 3,004 (+21357.14%)
Mutual labels:  deep-reinforcement-learning, ddpg
Machine Learning Is All You Need
🔥🌟《Machine Learning 格物志》: ML + DL + RL basic codes and notes by sklearn, PyTorch, TensorFlow, Keras & the most important, from scratch!💪 This repository is ALL You Need!
Stars: ✭ 173 (+1135.71%)
Mutual labels:  deep-reinforcement-learning, ddpg
Reinforcement Learning
🤖 Implements of Reinforcement Learning algorithms.
Stars: ✭ 104 (+642.86%)
Mutual labels:  deep-reinforcement-learning, ddpg
Deeprl
Modularized Implementation of Deep RL Algorithms in PyTorch
Stars: ✭ 2,640 (+18757.14%)
Mutual labels:  deep-reinforcement-learning, ddpg
deep rl acrobot
TensorFlow A2C to solve Acrobot, with synchronized parallel environments
Stars: ✭ 32 (+128.57%)
Mutual labels:  deep-reinforcement-learning, ddpg
Reinforcement-Learning-on-google-colab
Reinforcement Learning algorithm's using google-colab
Stars: ✭ 33 (+135.71%)
Mutual labels:  deep-reinforcement-learning, reinforcement-learning-algorithms
pytorch-distributed
Ape-X DQN & DDPG with pytorch & tensorboard
Stars: ✭ 98 (+600%)
Mutual labels:  deep-reinforcement-learning, ddpg
UAV-DDPG
Code for paper "Computation Offloading Optimization for UAV-assisted Mobile Edge Computing: A Deep Deterministic Policy Gradient Approach"
Stars: ✭ 133 (+850%)
Mutual labels:  reinforcement-learning-algorithms, ddpg
View All Similar Projects ➔

Continuous Control using Deep Reinforcement Learning on Unity ML Agent

Agents

Introduction

This repository contains a Deep Deterministic Policy Gradients (DDPG) agent running in the Unity ML Agent Reacher(https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Examples.md#reacher) environment. It can be used to train and evaluate the result of the training.

I use it for the purpose of learning DDPG agent in the context of continuous control of a agent.

The DDPG is implemented in Python 3 using PyTorch.

The full report can be found here. (https://github.com/kinwo/deeprl-continuous-control/blob/master/Report.pdf)

Environment

The 3D environment contains 20 double joined arms agents who can move freely to reach the target locations.

Goal

The goal is to control the 20 arms to move to their individual target locations and keep them there as many time steps as possible.

Environment Solved Criteria

The environment is considered solved when the average mean score of all agents reach 30+ in the last 100 epsisodes.

Rewards

A reward of +0.1 is provided for each step that each agent's hand is in the goal location independently.

Actions

Vector Action space: (Continuous) Size of 4, corresponding to torque applicable to two joints.

Spaces

The observation space is composed of 33 variables:
position, rotation, velocity, and angular velocities of the arm

Getting Started

  1. Install Unity ML https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Installation.md

  2. Download the Unity ML environment from one of the links below based on your OS:

Then unzip the file and place the file in this project folder.

  1. Create Conda Environment

Install conda from conda.io. Create a new Conda environment with Python 3.6.

conda create --name deeprl python=3.6
source activate deeprl
  1. Install Dependencies
cd python
pip install .

How to run the agent

To start training, simply open Continuous_Control.ipynb in Jupyter Notebook and follow the instructions there:

Start Jupyter Notebook

jupyter notebook

Trained model weights is included for quickly running the agent and seeing the result in Unity ML Agent. Simply skip the training step and run the last step of the Continuous_Control.ipynb

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].