In this environment, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of the agent is to maintain its position at the target location for as many time steps as possible.
The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1.
Please install Unity ML-Agents and make sure that the following packages are installed too:
- pandas
- numpy
- matplotlib
- torch
git clone https://github.com/QuantLandi/continuous_control_ddpg.git
cd continuous_control_ddpg
your-markdown-viewer report.md
jupyter notebook continuous_control_ddpg.ipynb
To train the agent and evaluate its performance, please open the continuous_control_ddpg.ipynb notebook and execute all cells. Before running all cells, change the file_name parameter to match the location of the Unity environment that you downloaded.
- Mac:
"path/to/Reacher.app" - Windows (x86):
"path/to/Reacher_Windows_x86/Reacher.exe" - Windows (x86_64):
"path/to/Reacher_Windows_x86_64/Reacher.exe" - Linux (x86):
"path/to/Reacher_Linux/Reacher.x86" - Linux (x86_64):
"path/to/Reacher_Linux/Reacher.x86_64" - Linux (x86, headless):
"path/to/Reacher_Linux_NoVis/Reacher.x86" - Linux (x86_64, headless):
"path/to/Reacher_Linux_NoVis/Reacher.x86_64"
For instance, if you are using a Mac, then you downloaded Reacher.app. If this file is in the same folder as the notebook, then the line below should appear as follows:
env = UnityEnvironment(file_name="Reacher.app")