/reinforcement-learning-collaboration-competition

Project 3 of Udacity's Deep Reinforcement Learning nanodegree program

Primary LanguageJupyter Notebook

Project 3: Collaboration and Competition

Introduction

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

Trained Agent

Reward

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.

State Space

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.

Goal

The task is episodic, and in order to solve the environment, your 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 2 (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.

Getting Started

  1. Follow the instructions from here for the setup

  2. 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.

Train Agent

Execute Tennis.ipynb to train your own agent! It is based on MADDPG Paper

The entire notebook can be executed by pressing play icon

Jupyter Image

The trained agents would automatically get saved in models/ folder for the algorithm

Folder Structure

  • agents contains the code for all the types of agents
  • buffers contains the code for replay buffer which all the algorithms use
  • models contains the saved models generates by the code
  • networks contains the code for neural networks being used by all the algorithms
  • noise contains all the noise models related with project
  • resources contains all the resources related with project