-
Notifications
You must be signed in to change notification settings - Fork 0
yzw19990124/DQN-Application-Project
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
Reiforcement Learning Double Q-Network DQN Project Description: CS138 Group Project - Double Q DQN Model Performance on Breakout Date Created: 12/01/2022 Python Environment: 3.6 above "trained-model" folder includes the trained two NN and output model. "output" folder includes the ouput graphs for trained and evaluation. "train_dqn.py" is the main DQN model py file. "config.py" is the configuration file for "train_dqn.py". MarsExplorer API Manual:https://github.com/dimikout3/MarsExplorer MarsExplorer API Installation: $ git clone https://github.com/dimikout3/GeneralExplorationPolicy.git $ pip install -e mars-explorer Following are the package needed for this project: import numpy import random import os import json import time import cv2 import gym import tensorflow tensorflow.keras.initializers tensorflow.keras.layers tensorflow.keras.optimizers tensorflow.keras.models
About
a project involving Deep Q-Networks (DQN) and Reinforcement Learning (RL) using Gym and Gridworld API
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published