Using DDPG , training 20 agents to play in the Reacher Unity Environment
This project works with the Reacher environment.
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 your 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.
It is recommended to follow the Udacity DRL ND dependencies instructions here
This project utilises Unity ML-Agents, NumPy and PyTorch
A prebuilt simulator is required in be installed. You need only select the environment that matches your operating system:
Linux: click here Mac OSX: click here Windows (64-bit): click here
Linux: click here Mac OSX: click here Windows (64-bit): click here
The file needs to placed in the root directory of the repository and unzipped.
Next, before starting the environment utilising the corresponding prebuilt app from Udacity Before running the code cell in the notebook, change the file_name
parameter to match the location of the Unity environment that you downloaded.
Then run the DDPG_Continuous_Control.ipynb
notebook using the drlnd kernel to train the DDPG agent.
Once trained the model weights will be saved in the same directory in the files checkpointactor.pth
and checkpointcritic.pth
.