This project uses 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.
There are 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.
The second version is useful for algorithms like PPO, A3C, and D4PG that use multiple (non-interacting, parallel) copies of the same agent to distribute the task of gathering experience.
Here, we only solve the first version of the environment, for a single agent.
The task is episodic, and in order to solve the environment, the agent must get an average score of +30 over 100 consecutive episodes.
The barrier for solving the second version of the environment is slightly different, to take into account the presence of many agents. In particular, the agents must get an average score of +30 (over 100 consecutive episodes, and over all 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 20 (potentially different) scores. We then take the average of these 20 scores.
- This yields an average score for each episode (where the average is over all 20 agents).
The environment is considered solved, when the average (over 100 episodes) of those average scores is at least +30.
-
If you are using Windows and just want to check out the solution for Version 1, you can use the provided binaries. Otherwise, download the appropriate environment from one of the links below. You need 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
(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 (version 1) or this link (version 2) 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 the root folder of this repository and unzip (or decompress) the file.
-
You can use the environment.yml to install all dependenies if you're using conda.
-
IMPORTANT: Make sure you have version 0.4 of mlagents! pip install mlagents==0.4
The last part of Continuous_Control.ipynb contains an adapation of DDPG to train a successful agent for Version 1 of the task! The files checkpoint_actor_solved.pth and checkpoint_critic_solved.pth contain the model of a trained agent.
Implement the distributed training to solve the second version of the environment with multiple agents.