https://github.com/alessandroleite/tennis-rl
Usage of Unity ML-Agents train two agents to play tennis
https://github.com/alessandroleite/tennis-rl
ddpg-agent deep-learning deep-reinforcement-learning maddpg reinforcement-learning unity-ml unity-ml-agents
Last synced: 7 months ago
JSON representation
Usage of Unity ML-Agents train two agents to play tennis
- Host: GitHub
- URL: https://github.com/alessandroleite/tennis-rl
- Owner: alessandroleite
- Created: 2020-05-11T20:10:41.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2022-11-21T21:56:50.000Z (almost 3 years ago)
- Last Synced: 2023-03-11T18:33:00.844Z (over 2 years ago)
- Topics: ddpg-agent, deep-learning, deep-reinforcement-learning, maddpg, reinforcement-learning, unity-ml, unity-ml-agents
- Language: Jupyter Notebook
- Homepage:
- Size: 4.29 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
[//]: # (Image References)
[image1]: https://user-images.githubusercontent.com/10624937/42135623-e770e354-7d12-11e8-998d-29fc74429ca2.gif "Trained Agent"
[image2]: https://user-images.githubusercontent.com/10624937/42135622-e55fb586-7d12-11e8-8a54-3c31da15a90a.gif "Soccer"
# Collaboration and Competition
## 1. Introduction
This project uses Unity ML-Agents [Tennis](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Learning-Environment-Examples.md#tennis) environment to train two agents to play tennis.
![Trained Agent][image1]
In this environment, two agents control rackets to bounce a ball over a net. If an agent hits the ball over the net, it receives a reward of +0.1. If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of -0.01. Thus, the goal of each agent is to keep the ball in play.
The observation space consists of 8 variables corresponding to the position and velocity of the ball and racket. Each agent receives its own, local observation. Two continuous actions are available, corresponding to movement toward or away from the net, and jumping.
The task is episodic, and in order to solve the environment, the agents must get an average score of +0.5 over 100 consecutive episodes, after taking the maximum over both 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 two potentially different scores. We then take the maximum of these 2 scores.
- This yields a single **score** for each episode.
The environment is considered solved, when the average over 100 episodes of those **scores** is at least +0.5.
## 2. Getting Started
1. Download the environment from one of the links below. You need to select only one environment that matches your operating system:
- Linux: [click here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P3/Tennis/Tennis_Linux.zip)
- Mac OSX: [click here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P3/Tennis/Tennis.app.zip)
- Windows (32-bit): [click here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P3/Tennis/Tennis_Windows_x86.zip)
- Windows (64-bit): [click here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P3/Tennis/Tennis_Windows_x86_64.zip)
(_For Windows users_) Check out [this link](https://support.microsoft.com/en-us/help/827218/how-to-determine-whether-a-computer-is-running-a-32-bit-version-or-64) 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](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-on-Amazon-Web-Service.md)), then please use [this link](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P3/Tennis/Tennis_Linux_NoVis.zip) to obtain the "headless" version of the environment. You will **not** be able to watch the agent without enabling a virtual screen, but you will be able to train the agent. (_To watch the agent, you should follow the instructions to [enable a virtual screen](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-on-Amazon-Web-Service.md), and then download the environment for the **Linux** operating system above._)
2. Place the file in the `env` directory and unzip it.
## 3. Requirements
This project requires **Python 3.6** and for the libraries check the `requirements.txt` file. In short, the required libraries are:
- [NumPy](http://www.numpy.org/)
- [Matplotlib](https://matplotlib.org/)
- [Torch](https://pytorch.org)
- [UnityAgents](https://github.com/Unity-Technologies/ml-agents)
## 4. Instructions
Follow the instructions in `Tennis.ipynb` to start training your own agent!
## 5. References
1. Lillicrap, Timothy P., Jonathan J. Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. "Continuous control with deep reinforcement learning." arXiv preprint arXiv:1509.02971. 2015.
2. Lowe, Ryan, Yi I. Wu, Aviv Tamar, Jean Harb, OpenAI Pieter Abbeel, and Igor Mordatch. "Multi-agent actor-critic for mixed cooperative-competitive environments." In Advances in neural information processing systems, pp. 6379-6390. 2017.