For this project, we 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, 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 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.
-
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 "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.)
-
Place the file in this GitHub repository folder and unzip (or decompress) the file.
Run pip install -r requirements.txt to install all required python libraries needed to run this project locally. We suggest that you create a virtual environment first. To do this, using python's virtualenv package, follow the instructions here.
Follow the instructions in Tennis.ipynb to get started with training your own agent!
To run the model without the jupyter notebook, you simply need to run the main.py script, modifying the following
arguments if you need to:
usage: main.py [-h] --seed SEED [--buffer_size BUFFER_SIZE]
[--discount DISCOUNT] [--target_mix TARGET_MIX]
[--lr_actor LR_ACTOR] [--lr_critic LR_CRITIC]
[--learn_every LEARN_EVERY] [--learn_number LEARN_NUMBER]
[--epsilon EPSILON] [--epsilon_decay EPSILON_DECAY]
[--ou_noise_mu OU_NOISE_MU] [--ou_noise_sigma OU_NOISE_SIGMA]
[--ou_noise_theta OU_NOISE_THETA] [--batch_size BATCH_SIZE]
[--reacher_fp REACHER_FP] [--fc1_units FC1_UNITS]
[--fc2_units FC2_UNITS] [--max_episodes MAX_EPISODES]
[--add_noise [ADD_NOISE]]