Udacity Deep Reinforcement Learning Nanodegree is MOOCs lecture by Udacity in which DeepRL experts teach basic knowledge and implementation techniques about Deep RL via online video (mainly Youtube contents), and there are a lot of implementation tutorials in which each student has to implement various DeepRL algorithms.
This repository of DeepRL source code is work of 1st "Project" in this Nanodegree. This is at the end of Lecture Part2, Value-Based Methods including Deep Q-Learning and other developed methods (Double DQN, Prioritized Replay..) The project goal is to implement smart agent walking around game simulator which is created by using Unity ML-Agents(github repository)
In the simulator, there are two types of bananas, yellow ones and blue ones. If he catches yellow one, he gets positive reward (+1). But if he catches blue one, he gets negative reward (-1). Thus, the goal of the agent is to collect as many yellow bananas as possible while avoiding blue bananas.
Students need to implement DeepRL agent using Python and Pytorch.
The simulation contains a single agent that navigates a large environment. At each time step, it has four actions at its disposal:
0- walk forward1- walk backward2- turn left3- turn right
The state space has 37 dimensions and contains the agent's velocity,
along with ray-based perception of objects around agent's forward direction.
The task is episodic, and in order to solve the environment, the agent must get an average score of +13 over 100 consecutive episodes.
-
Check this nanodegree's prerequisite, and follow the instructions.
-
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
bin/directory, and unzip (or decompress) the file.
To train the agent, start jupyter notebook, open TrainDQN.ipynb
and execute! For more information, please check instructions
inside the notebook.
- Performance Report : Result report of training score when using Double-DQN as agent.