DDPG implementation for continuous action space
The environment is based on Unity ML-agents.
Note: The Unity ML-Agent team frequently releases updated versions of their environment. We are using the v0.4 interface. The project environment provided by Udacity is similar to, but not identical to the Reacher environment on the Unity ML-Agents GitHub page.
For this project, Udacity provides two separate versions of the Unity environment:
- The first version contains a single agent.
- The second version contains 20 identical agents, each with its own copy of the environment.
I have decided to go with the second version. The agents thus need to be trained so they get an average score of +30 (over 100 consecutive episodes, and over all agents)
-
To begin with, you need to configure a Python 3.6 / PyTorch 0.4.0 environment with the requirements described in Udacity repository
-
Then you need to clone this project and have it accessible in your Python environment
-
For this project, you will not need to install Unity. You need to only select the environment that matches your operating system:
-
Version 1: One (1) Agent
- Linux: click here
- Mac OSX: click here
- Windows (32-bit): click here
- Windows (64-bit): click here
-
Version 2: Twenty (20) Agents
- Linux: click here
- Mac OSX: click here
- Windows (32-bit): click here
- Windows (64-bit): click here
-
-
Finally, you can unzip the environment archive in the project's environment directory and set the path to the UnityEnvironment in the code.
The configuration for the environement, the agent and the DDPG parameters are mentioned in the config file.