drl_reacher | DDPG implementation for Reacher Unity environment
kandi X-RAY | drl_reacher Summary
kandi X-RAY | drl_reacher Summary
drl_reacher is a HTML library. drl_reacher has no bugs, it has no vulnerabilities, it has a Strong Copyleft License and it has low support. You can download it from GitHub.
For this project, I have trained an agent for solving a continous control problem: move a 2 sections joined arm to a target area. In this environment, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of your agent is to maintain its position at the target location for as many time steps as possible. The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1. There are 2 versions of this environment: the first version contains a single agent. The second version contains 20 identical agents, each with its own copy of the environment. I have chosen the second one that is useful for algorithms like PPO, A3C, and D4PG that use multiple (non-interacting, parallel) copies of the same agent to distribute the task of gathering experience. The barrier for solving the second version of the environment is slightly different, to take into account the presence of many agents. In particular, your agents must get an average score of +30 (over 100 consecutive episodes, and over all agents). Specifically,. After each episode, we add up the rewards that each agent received (without discounting), to get a score for each agent. This yields 20 (potentially different) scores. We then take the average of these 20 scores.
For this project, I have trained an agent for solving a continous control problem: move a 2 sections joined arm to a target area. In this environment, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of your agent is to maintain its position at the target location for as many time steps as possible. The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1. There are 2 versions of this environment: the first version contains a single agent. The second version contains 20 identical agents, each with its own copy of the environment. I have chosen the second one that is useful for algorithms like PPO, A3C, and D4PG that use multiple (non-interacting, parallel) copies of the same agent to distribute the task of gathering experience. The barrier for solving the second version of the environment is slightly different, to take into account the presence of many agents. In particular, your agents must get an average score of +30 (over 100 consecutive episodes, and over all agents). Specifically,. After each episode, we add up the rewards that each agent received (without discounting), to get a score for each agent. This yields 20 (potentially different) scores. We then take the average of these 20 scores.
Support
Quality
Security
License
Reuse
Support
drl_reacher has a low active ecosystem.
It has 0 star(s) with 0 fork(s). There are 1 watchers for this library.
It had no major release in the last 6 months.
drl_reacher has no issues reported. There are no pull requests.
It has a neutral sentiment in the developer community.
The latest version of drl_reacher is current.
Quality
drl_reacher has no bugs reported.
Security
drl_reacher has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.
License
drl_reacher is licensed under the GPL-3.0 License. This license is Strong Copyleft.
Strong Copyleft licenses enforce sharing, and you can use them when creating open source projects.
Reuse
drl_reacher releases are not available. You will need to build from source code and install.
Installation instructions, examples and code snippets are available.
Top functions reviewed by kandi - BETA
kandi's functional review helps you automatically verify the functionalities of the libraries and avoid rework.
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of drl_reacher
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of drl_reacher
drl_reacher Key Features
No Key Features are available at this moment for drl_reacher.
drl_reacher Examples and Code Snippets
No Code Snippets are available at this moment for drl_reacher.
Community Discussions
No Community Discussions are available at this moment for drl_reacher.Refer to stack overflow page for discussions.
Community Discussions, Code Snippets contain sources that include Stack Exchange Network
Vulnerabilities
No vulnerabilities reported
Install drl_reacher
I have used Linux. You can download the version for your SO, but remember to point to your Reacher environment folder:. There are 2 available versions: 1 arm and 20 arms in parallel. Is you may notice, the notebook (Reacher_Linux_20) containing the solution is calling to the 20 arms environment. Due to issues with conda, not only environment.yml is provided. Another file (requirements.txt) is also attached and should be taken into account. Next with pip: pip install -r requirements.txt.
Download the environment from one of the links below. You need only select the environment that matches your operating system: Linux: click here Mac OSX: click here Windows (32-bit): click here Windows (64-bit): click here (For Windows users) Check out this link if you need help with determining if your computer is running a 32-bit version or 64-bit version of the Windows operating system. (For AWS) If you'd like to train the agent on AWS (and have not enabled a virtual screen), then please use this link to obtain the environment.
Place the file in the unziped folder, and unzip (or decompress) the file.
Create a virtual environment with anaconda and install packages: conda env create -f environment.yml.
Activate the virtual environment: source activate <name of the env>.
Install more packages:
Launch jupyter notebook: jupyter notebook Navigation.ipynb
Execute cells: just first cell (for imports).
Download the environment from one of the links below. You need only select the environment that matches your operating system: Linux: click here Mac OSX: click here Windows (32-bit): click here Windows (64-bit): click here (For Windows users) Check out this link if you need help with determining if your computer is running a 32-bit version or 64-bit version of the Windows operating system. (For AWS) If you'd like to train the agent on AWS (and have not enabled a virtual screen), then please use this link to obtain the environment.
Place the file in the unziped folder, and unzip (or decompress) the file.
Create a virtual environment with anaconda and install packages: conda env create -f environment.yml.
Activate the virtual environment: source activate <name of the env>.
Install more packages:
Launch jupyter notebook: jupyter notebook Navigation.ipynb
Execute cells: just first cell (for imports).
Support
For any new features, suggestions and bugs create an issue on GitHub.
If you have any questions check and ask questions on community page Stack Overflow .
Find more information at:
Reuse Trending Solutions
Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items
Find more librariesStay Updated
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page