ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

Code

• github.com/mwydmuch/ViZDoom
  Officialtf★ 0
• github.com/hegde95/ViZDoom_with_Sound
  pytorch★ 1
• github.com/apollopower/DOOM-AI
  tf★ 0
• github.com/icmlanon58443043/vizdoomicmlanon
  tf★ 0
• github.com/chengyu2/vizdoom_rl_community_canberra
  none★ 0
• github.com/nolanwinsman/Team-Doom
  pytorch★ 0
• github.com/sagpant/ViZDoom
  tf★ 0
• github.com/farama-foundation/vizdoom
  pytorch★ 0
• github.com/NervanaSystems/coach
  tf★ 0
• github.com/icmlanon58443043/vizdoom
  tf★ 0

Abstract

The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 games, however, do not resemble real-world tasks since they involve non-realistic 2D environments and the third-person perspective. Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world. The software, called ViZDoom, is based on the classical first-person shooter video game, Doom. It allows developing bots that play the game using the screen buffer. ViZDoom is lightweight, fast, and highly customizable via a convenient mechanism of user scenarios. In the experimental part, we test the environment by trying to learn bots for two scenarios: a basic move-and-shoot task and a more complex maze-navigation problem. Using convolutional deep neural networks with Q-learning and experience replay, for both scenarios, we were able to train competent bots, which exhibit human-like behaviors. The results confirm the utility of ViZDoom as an AI research platform and imply that visual reinforcement learning in 3D realistic first-person perspective environments is feasible.

Tasks

Reproductions