Dark Forest is an open-source 3D interactive battleground and survival sandbox game. The basic playing logic is to survive till the game ends. The operation for a player includes horizontal and vertical movement, shoot, drink and eat. HP will be affected by hunger, thirstiness, and also possible fight with other players. Since the resources (ammo, food, water are decreasing in time), only one will survive till the end as winner.
Dark Forest is a course project for CSCI 527 Applied Machine Learning for Games. The main goal is to develop a game environment for reinforcement learning training. Besides, to fully utilize the trained reinforcement learning model to improve gamers’ satisfaction, gamers can interact with the NPC with designated difficulties due to reinforcement learning models of different types.
This game is a multi-player game environment. High-level and low-level development are both required in this project. Low-level development focuses on the game infrastructure development, including character mods, action, operation. High-level development focuses on implementing API for ML-Agent package to train reinforcement learning models and inference from previous models.
NPC: A non-player character (NPC) is any character in a game which is not controlled by a player HP: Health or hit points (commonly abbreviated to HP) is an attribute in tabletop role-playing games and video games that determines the maximum amount of damage that a character or object can take.
Unity Version 2019.4.18 ML Agent 1.6.0 preview