I'd like to see a single-player bot that can do human-level speedruns and/or beat stuff like <a href="https://www.twitch.tv/blooditekrypto/v/30795033" rel="nofollow">https://www.twitch.tv/blooditekrypto/v/30795033</a><p>Baby steps. Beating other bots in deathmatch is a good start. I love that they only use the rocket launcher, giving the careless bot an equal chance of blowing itself up.<p>Parsing what's on the screen in Doom is potentially a lot easier than in modern games: since there is no texture filtering or anti-aliasing, and due to the 2.5D perspective, most vertical runs of pixels on the screen map exactly to (linearly?) scaled columns in wall textures or sprites. I would not be surprised if you could come up with a fairly simple algorithm to determine the exact position and orientation of the player and the objects on screen within the map, without any real AI/learning involved.
Related: <a href="https://www.newscientist.com/article/2076552-google-deepmind-ai-navigates-a-doom-like-3d-maze-just-by-looking/" rel="nofollow">https://www.newscientist.com/article/2076552-google-deepmind...</a><p><i>Google DeepMind AI navigates a Doom-like 3D maze just by looking</i><p>Paper: <a href="http://arxiv.org/abs/1602.01783" rel="nofollow">http://arxiv.org/abs/1602.01783</a>
Google cache: <a href="http://webcache.googleusercontent.com/search?q=cache:bVb0ETVF1p8J:vizdoom.cs.put.edu.pl/competition-cig-2016+&cd=1&hl=en&ct=clnk&gl=us" rel="nofollow">http://webcache.googleusercontent.com/search?q=cache:bVb0ETV...</a>
Interesting article and poses the question and what I would theorize is the correct way for A.I. to learn how to be more human or machine learn is in a virtual environment. i.e. create a 3D based game to teach it how to interact in the physical world in order for robotic A.I. advancement and human interaction. Similar to Google Drive then test on the road in real-life.<p>To the point on visual processing a stealth A.I. (not for long) working in this space is Magic Pony Technology (<a href="http://www.magicpony.technology/" rel="nofollow">http://www.magicpony.technology/</a>) operating from London and guys I spotted at London A.I. who have previously hosted Prediction IO and Swiftkey at their last events.<p>Another caveat for this test is sound, human players will have audio but the A.I. will be purely visual so a slight disadvantage.<p>We are working on speech-to-text and text-to-speech technology for our A.I. voice enabled finance assistant which is in beta at WealRo (<a href="http://www.wealro.com" rel="nofollow">http://www.wealro.com</a>) with a view to enabling a visual face recognition at some point in order for the A.I. to gather information from facial expressions. Always happy to get any thoughts on the potential usefulness of such an integration?
The site seems to have moved to <a href="http://www.cs.put.poznan.pl/visualdoomai/competition-cig-2016.html" rel="nofollow">http://www.cs.put.poznan.pl/visualdoomai/competition-cig-201...</a>
The question seems flawed, as having an AI making decisions only based on visual information is basically confusing how you get the information (visual) and what information the AI get (only limited information, similar to what the player has). Two different problems that can be solved completely independently. The first problem makes no sense for a game (how intensive would be the computation), while the latter one could be very interesting, since it would rely on designing the AI more like a natural player. The catch however is that it's a "could", in itself there is no reason to imagine such AIs would make the game better in any way (over "cheating" AI's).
[Content after page loading]<p>Motivation<p>Doom has been considered one of the most influential titles in the game industry since it popularized the first-person shooter (FPS) genre and pioneered immersive 3D graphics. Even though more than 20 years have passed since Doom’s release, the methods for developing AI bots have not improved significantly in newer FPS productions. In particular, bots have still to “cheat” by accessing game’s internal data such as maps, locations of objects and positions of (player or non-player) characters. In contrast, a human can play FPS games using a computer screen as the only source of information. Can AI effectively play Doom using only raw visual input?
Goal<p>The participants of the Visual Doom AI competition are supposed to submit a controller (C++, Python, or Java) that plays Doom. The provided software gives a real-time access to the screen buffer as the only information the agent can base its decision on. The winner of the competition will be chosen in a deathmatch tournament.
Machine Learning<p>Although the participants are allowed to use any technique to develop a controller, the design and efficiency of the Visual Doom AI environment allows and encourages participants to use machine learning methods such as reinforcement deep learning.
Competition Tracks
1. Limited deathmatch on a known map.<p>The only available weapon is the Rocket Launcher, with which the agents start. The agents can also gather Medikits and ammo.
2. Full deathmatch on an unknown map.<p>Different weapons and items are available. Two maps are provided for training. The final evaluation will take place on three maps unknown to the participants beforehand.
Important Dates<p><pre><code> 31.05.2016: Warm-up deathmatch submission deadline
15.08.2016: Final deathmatch submission deadline
20-23.09.2016: Results announcement (CIG)
</code></pre>
Contact<p><pre><code> For announcements and questions subscribe to vizdoom@googlegroups.com
Bugs: Open a new GitHub ticket
</code></pre>
Getting started<p><pre><code> Download (or compile) the ViZDoom environment.
Follow the instructions.
</code></pre>
What will the Deathmatch Look Like?<p>Your controller will fight against all other controllers for 10 minutes on a single map. Each game will be repeated 12 times for track 1 and 4 times for track 2, which involves three maps. The controllers will be ranked by the number of frags.<p><pre><code> In the case of lots of submissions, we will introduce some eliminations.
</code></pre>
Technical Information<p><pre><code> Each controller will be executed on a separate machine having a single CPU and GPU at its only disposal.
The machine specification: Intel(R) Core(TM) i7-4790 CPU @ 3.60GHz + GTX 960 4GB
Operating system: Windows or Ubuntu Linux 15.04
</code></pre>
How to Submit my Entry?<p>To accept your submission we will need the following data:<p><pre><code> name of the team
team members and their affiliations
max. 2 pages description of the method used to create the controller (pdf)
a list of (sensible) software requirements for the agent to run (ask beforehand)
a link to the source code of your controller and additional files (max 1GB in total)
an instruction how to build and execute the controller
</code></pre>
The form to submit the above data will be provided later.<p><pre><code> In the spirit of open science, all submissions will be published on this website after the competition is finished.
</code></pre>
Organizers<p>Wojciech Jaśkowski, Michał Kempka, Marek Wydmuch, Jakub Toczek