• Stars
    star
    131
  • Rank 274,273 (Top 6 %)
  • Language
    Python
  • License
    MIT License
  • Created over 7 years ago
  • Updated over 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Reinforcement learning models in ViZDoom environment

DoomNet

DoomNet is a ViZDoom agent trained by reinforcement learning. The agent is a neural network that outputs a probability of actions given only pixels from the screen buffer and set of game variables.
DoomNet is a 1st Runner-Up at Visual Doom AI Competition 2018.

What a simple behavior tree can do

DoomNet on a simple behavior tree

1st Runner-Up at Visual Doom AI Competition 2018

DoomNet track1, submission 0

Visual Doom AI Competition 2017

Joint work with Bobby DeSimone

DoomNet's view is at left in the middle row
DoomNet track1, elimination round 2017

D3 Battle

DoomNet trained on D3-battle config

Health Gathering

DoomNet trained on health gathering config

Rocket Basic

DoomNet trained on basic rocket config

Basic

DoomNet trained on basic config