This project is Ben Hosken's submission to for the Deep RL Nanodegree project 3. The environment was solved in 290 episodes using the DDPG algorithm with a a single agent model being trained with both players.
This project uses the Tennis environment.
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, 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.
The following prerequists are required:
unityagents numpy torch matplotlib
The Unity environment can be downloaded as follows
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](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._)
Unzip the download and place the file in the root directory for the project e.g. p3_collab-compet/Tennis.app <- on OS X
Open Tennis.ipynb and run through the steps to train your own agent or run a trained agent.
The agent has already been trained and the checkpointed weights have been saved at checkpoint_actor.pth and checkpoint_critic.pth