Continuous control project #2 for UDACITY course Deep Reinforcement Learning
We are working 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.
We are solving the first version of the environment with a single agent.
The task is episodic, and in order to solve the environment, your agent must get an average score of +30 over 100 consecutive episodes.
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
p2_continuous-control/folder, and unzip (or decompress) the file.
Open Continuous_Control.ipynb and run all cells one by one. The notebook imports the class of Agent from DDPG_agent.py.
Running the cell of step 3 will start the training of the agent. The training will end once mean reward over 100 episodes reaches at least 30 or the maximum number of total episodes (episodes).