UDACITY DRLN Project 3: Tennis Environment
For this project, you will work with 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.
UDACITY workspace was used for the project. The environment uses Python 3.6. The following pip libraries are needed:
- torch: 0.4.0
- numpy: 1.12.1
- unityagents
- OpenAI Gym (https://github.com/openai/gym)
Optional: if not running on workspace, clone the DRLND repo https://github.com/udacity/deep-reinforcement-learning#dependencies, install dependencies and download the Unity Environment.
-
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 DRLND GitHub repository, in the
p3_collab-compet/folder, and unzip (or decompress) the file.
Open Tennis.ipynb and run all cells one by one. The notebook imports the class of MaDDPGAgent from MaDDPG.py.
Running the cell of step 3 will start the training of the agent. The training will end once the mean reward (each episode, the maximum reward of the 2 agents is stored) over 100 episodes is greater than 0.5 or the maximum number of total episodes (episodes).