Skip to content

Latest commit

 

History

History
66 lines (49 loc) · 4.1 KB

README.md

File metadata and controls

66 lines (49 loc) · 4.1 KB
Raw

Project 3: Collaboration and Competition

Introduction

For this project, you will work with the Tennis environment.

Trained Agent

Environment Description

States

  • The observation space consists of 8 dimensions.
  • It is corresponding to the position and velocity of the ball and racket.
  • Two agents control rackets to bounce a ball over a net. Each agent receives its own, local observation.

Actions

  • Two continuous actions are available, corresponding to movement toward (or away from) the net, and jumping.

Rewards

  • An agent receives a reward of +0.1, if an agent hits the ball over the net.
  • If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of -0.01.

Goal

  • The goal of the two agents is to collaborate to keep the ball in play.
  • The environment is considered solved, when the average (over 100 episodes) of those scores is at least +0.5.

Project Structure

The repository contains the following files.

  • Tennis.ipynb Contains the agent training code for Unity Tennis environment.
  • maddpg_agent.py Contains MADDPG based agent implemenation.
  • model.py Contains actor and critic network.
  • noise.py Contians Ornstein-Uhlenbeck noise process utility class.
  • replay_buffer.py Contains replay buffer utility class.
  • train.py Contains training utility methods.
  • main.py It is an entry file for training in normal python way. It is an alternative to Tennis.ipynb.
  • checkpoint_actor_0/1.pth and checkpoint_critic_0/1.pth are pre-trained model parameters' file.
  • Report.ipynb Contains project write-up or report, which details the implementation and algorithm.

Getting Started

  1. Install Anaconda(https://conda.io/docs/user-guide/install/index.html)
  2. Install dependencies by issue:
pip install -r requirements.txt

  1. Download the environment from one of the links below. You need only select the environment that matches your operating system:

    (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 "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, and then download the environment for the Linux operating system above.)

  2. Place the file in the root folder, and unzip (or decompress) the file.

Instructions

Follow the instructions in Tennis.ipynb to get started with training, or directly jump to Watch Smart Agent using pre-trained weights, checkpoint_actor_0/1.pth and checkpoint_critic_0/1.pth, to watch the performance of the two trained agents.