ViZDoom Competitions: Playing Doom from Pixels

2018-09-10 · Marek Wydmuch, Michał Kempka, Wojciech Jaśkowski

This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To play well, the bots needed to understand their surroundings, navigate, explore, and handle the opponents at the same time. These aspects, together with the competitive multi-agent aspect of the game, make the competition a unique platform for evaluating the state of the art reinforcement learning algorithms. The paper discusses the rules, solutions, results, and statistics that give insight into the agents' behaviors. Best-performing agents are described in more detail. The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game. The paper also revisits the ViZDoom environment, which is a flexible, easy to use, and efficient 3D platform for research for vision-based reinforcement learning, based on a well-recognized first-person perspective game Doom.

📄 PDF Abstract BibTeX arXiv:1809.03470

Code (7)

mwydmuch/ViZDoom 공식 구현 tf

farama-foundation/vizdoom pytorch

hegde95/ViZDoom_with_Sound pytorch

icmlanon58443043/vizdoom tf

icmlanon58443043/vizdoomicmlanon tf

nolanwinsman/Team-Doom pytorch

sagpant/ViZDoom tf

Tasks

Navigatereinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Autoencoder-augmented Neuroevolution for Visual Doom Playing

2017-07-12 · Samuel Alvernaz, Julian Togelius

Neuroevolution has proven effective at many reinforcement learning tasks, but does not seem to scale well to high-dimensional controller representations, which are needed for tasks where the input is raw pixel data. We p…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Superior Performance with Diversified Strategic Control in FPS Games Using General Reinforcement Learning

2021-09-29 · Shuxing Li, Jiawei Xu, Chun Yuan, Peng Sun 외

This paper offers an overall solution for first-person shooter (FPS) games to achieve superior performance using general reinforcement learning (RL). We introduce an agent in ViZDoom that can surpass previous top agents …

FPS Games General Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

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

2016-05-06 · Michał Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek 외

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 game…

Atari Games FPS Games Game of Doom Q-Learning+3

Robust Dual View Deep Agent

2018-04-13 · Ibrahim M. Sobh, Nevin M. Darwish

Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling

2018-01-03 · Christopher Schulze, Marcus Schulze

ViZDoom is a robust, first-person shooter reinforcement learning environment, characterized by a significant degree of latent state information. In this paper, double-Q learning and prioritized experience replay methods …

Q-Learning Reinforcement Learning