Leaderboard

Hello hello friends! It has been some time since I posted about the mod but worry not! We aren't dead yet. Work has been pretty slow. Managing life and prioritizing stuff has had me all over the place but work continues on the mod! Currently, only one of the factions units is really done but we don't have any art for them and have just been using the assets provided by 0 A.D. which makes it a little confusing and very cobbled together. We did manage to find two artists who have been working on the project but they've been pretty slow and fairly unresponsive unfortunately so the hunt continues to find good artists that are decently reliable! I've not been able to work on any of the art myself either because I haven't had the energy. So, at the moment the mod is progressing but only though the programming side. Even then it is still slow. Sorry for the random updates here and there and bouts of silence! We are trying our best!

Hello everyone, This year and for the past three years 0 A.D. was holding a stand at the FOSDEM. Like every time, it was a very great experience for me, and I was happy to be able to join @Itms, @plumo, @implodedok, @FeXoR, @bb_, @Imarok, @vladislavbelov and @fabio in this adventure. This year was a bit special because I got to co-host a game dev room with the guys at Godot thanks to Akien and Straton and of course to all the people I convinced to give talks and the people that attended said talks. I think the dev room was an overall positive experience so it's great! You can find the videos here. Our room was K.3.201. Some videos might not have been uploaded yet. There were a lot of interesting talks, especially the one about the Spring engine going to Steam. I got to talk a bit with the guys at the GSOC stand and they apparently knew us, so maybe we'll be more lucky this year. I got to meet a lot of people for the first time, some of the above team members, but also @Krinkle, @balduin. I also met @oSoMoN with who we discussed a potential better usage of the Snap Packages for 0 A.D. The idea would be to offer special features to be tested as snap packages on something like Kiwit CMS. By using this specific platform we would be able to set up test scenarios for things not covered by CI and unit tests. I also had the great honor to meet with Ton Roosendal (the CEO of Blender) and Dalai Felinto. We had an informal chat at our stand about our usage of Blender. Bernard Tyers asked me to give a talk at the design dev room next year and I think I'm gonna deliver. The Raspberry Pi 4 I brought had quite a nice success as it caught the eye and people were amazed that it could run on such a low end device. A few people were interested in helping out. We are looking forward to hearing from them. Thanks for all the people who gave us donations! For those who paid for music CDs I hope you'll enjoy them. For those that could not get one you can grab it here. See you all next year, or at the next FLOSS event that we will attend which will likely be JDLL in Lyon, France.

Hello everyone, I have been interested in making it possible to explore applications of machine learning in 0 AD (as some of you may have gathered from https://trac.wildfiregames.com/ticket/5548 ). I realized that I haven't really explained very thoroughly my interest and motivation so I figured I would do so here and see what everyone thinks! tl;dr - At a high level, I think that adding an OpenAI gym-like interface* could be a cool addition to 0 AD that would benefit both 0 AD (technically and in terms of publicity) as well as the research community in machine learning and AI. I go into the specifics below as well as discuss other potential avenues for integrating/leveraging machine learning: Potential Machine Learning Problems/Applications Intelligent unit control (micromanagement) I have an example where an AI learns to kite with cavalry archers when fighting infantry at https://github.com/brollb/simple-0ad-example. This is probably one of the easiest problems to explore as it can be done progressively starting with small, clearly defined scenarios using the functionality added in the beforementioned ticket. That said, there are still some of the standard challenges present with machine learning around ensuring that the AI has been trained on sufficiently diverse scenarios so that it doesn't ever encounter something new and behave incorrectly. As far as potential impact on the game, automatic micromanagement could be interesting for either a component in an otherwise scripted AI such as Petra or as a way to make the units more intelligent as they gain experience. That is, I could imagine that as the units gain more experience, they could also start having improved tactical behavior, such as kiting, automatically. Enemy AI Trained Entirely with Reinforcement Learning This is actually very difficult although it has been recently done in StarCraft 2 (https://deepmind.com/blog/article/alphastar-mastering-real-time-strategy-game-starcraft-ii). Although I think this could be fun for people to try to do, I wouldn't have high expectations on this front for awhile because it is a very hard problem for ML to solve - especially given the large number of different civilizations, maps, resource types, etc. Enemy AI with Scripting and Learned Components This is referring to a generic version of what I mentioned under "intelligent unit control". Essentially, there are a lot of opportunities to incorporate learned components into an otherwise scripted AI. From a technical perspective, this makes the machine learning problem much easier/tractable while still enabling more intelligent behavior from the built in AI. There are many different examples of intelligent components that could be incorporated. For example, it could try to predict the outcome of a battle (to determine if we should retreat) or try to imitate various high-level human strategies (such as predicting what a human might target for an attack). Quantitative Game Balancing This is a very interesting problem and I find 0 AD to be a particularly unique opportunity for exploring it. Essentially, the idea is that there are many different parameters in a game (such as attack damage for each unit, etc) which are quite difficult to tune without making the game imbalanced and one of the civilizations/strategies OP. (I don't think I need an example for this community but I enjoyed watching https://www.gdcvault.com/play/1012211/Design-in-Detail-Changing-the.) This problem is nontrivial since detecting overpowered strategies really requires an understanding of the way various aspects of the game can be exploited. Although this is a nontrivial problem, I find it to be an exciting opportunity for 0 AD to gain publicity and for researchers to have a sandbox in which they can explore this research question in an actual game (rather than a trivial, toy environment). That is, many of the other environments used in reinforcement learning research are either open source toy environments (eg, CartPole) or proprietary games which cannot be modified (eg, StarCraft 2). There has been a bit of related research in detecting imbalance in complex games like StarCraft 2 as well as balancing simpler games but as proprietary games will not be exposing the parameters used for the units (and other aspects of the game), automatic game balancing approaches are limited. Being an open source game that people actually play, 0 AD provides a really exciting opportunity for research in this direction as the parameters of the game are not proprietary and could be modified programmatically enabling researchers to explore this rather complex problem. For the 0 AD community, enabling researchers to conduct this type of research in the game itself should make it much easier to be able to incorporate any results of such research into the game making 0 AD more fun and an even better game! Imitation Learning Training the AI to imitate humans is worth mentioning although the impact on the game is likely to be in one of the beforementioned ways. Imitation learning, unlike reinforcement learning, is training the AI using expert demonstrations of gameplay. It is often used as a method for essentially initializing the AI to something reasonable before training it further with reinforcement learning (ie, training the AI using a reward rather than example). Imitation learning can arguably be more valuable for game development given that it can more directly instill various human-like behaviors (hopefully making the gameplay more engaging and interesting) rather than simply trying to maximize some reward or score in the game. Techniques to Train and Understand AI Agents This is more of a general research direction that I find interesting (and is similar to research that I have done in the past). Essentially, this is exploring the means by which the game developer can use the various methods of instilling behavior into an AI (programming, reinforcement learning, imitation learning) to create the desired behavior (and game experience). This is a bit of both a human-computer interaction (HCI) and machine learning question (also related to machine teaching). To give a more concrete example, this would include exploring the behavior of a trained RL agent in the game, correcting these behaviors, and perhaps trying to detect potentially incorrect behaviors to raise to the user automatically. 0 AD is well suited for this type of research for the same reasons that it is well suited for exploring game balance - most games used in research are either proprietary or not something people would actually play. Optimizing Existing Game Parameters (Relatively Easy) There are some existing machine learning tricks that could be used to make other sorts of improvements to the game rather than explore research questions. A while back, I was playing around with CMAES (a machine learning technique to optimize a set of parameters given a "fitness function") to improve some of the sort of magic numbers used within Petra such as "popPhase2" and "armyMergeSize". Essentially, this made it possible to find values for these parameters which would improve the AI's ability to win when playing against the standard Petra agent (on the hardest difficulty). Although I don't find this as interesting as the other areas, it is a useful tool that could be nice to apply to other aspects of the game. Overall, I think it would be really exciting to be able to explore some of the research questions in 0 AD as I think it could be beneficial both to researchers but also would make it easier to incorporate the results of this research into 0 AD (making it an even better game!). Of course, this is only true if the functionality required to be added to 0 AD is easy to maintain and doesn't add overhead taking away from the development of the core game features and functionality. I am also hopeful that incorporating some of these machine learning capabilities could also be beneficial to the community and raise awareness of 0 AD! As far as technical requirements, I made an RPC interface for controlling the AI from Python (because the majority of machine learning tools are in Python). This makes it possible to explore 1, 2, and 3 as well as provides necessary functionality for 4, 5, and 6. As mentioned above, I have an example of #1 on GitHub and I think this could make for really interesting undergraduate projects (as well as potentially interesting integrations into the game). However, I think 0 AD is a particularly unique opportunity for exploration of 4 and 6. Game balancing (#4) still requires the ability to programmatically edit the unit parameters which I have explored a little bit but haven't added to the game. If this is something that others find interesting (and wouldn't mind me asking a few questions ), I would be open to adding this as well. Anyway, I find these machine learning problems and applications quite exciting both for 0 AD and for AI/ML research but I want to know what the rest of the community thinks! Let me know what you think or if you have any questions/comments! * I say *OpenAI gym-like* because a gym environment requires an observation space (numerical representation of the world for the AI), action space (numerical representation of the actions the AI can perform), and reward function to be defined. It isn't clear what the most appropriate choices for these would be (and they could vary based on the specific scenario) so I would prefer making more of a "meta-gym" where it is basically an OpenAI gym that needs the user to specify these values.

Alright. If you want me to have a look I can it's nice to see new modders active!

Yeah, we do have one but its super bare-bones because I keep forgetting to upload the files that I have there. At the moment, getting into contact with them has been the main issue, they're in very different time zones and they don't make any effort to reach out to me or anyone on the team. I do recognize they have lives outside of modeling and what not but it wouldn't hurt to give an update to me. Also there is a bit of a language barrier, neither of them speak english as their native tongue so that hampers the process a little as well. Anyway, not here to complain to the world lol, as far as I know they've done a lot of research on the engine themselves and seem confident in their ability so I hope it pans out in the end!

Hey there @DeadTom, Nice to see it's still being worked on. Maybe the artists need a bit of help. If so you can send them to me and I'll be happy to help. The game engine is always a bit overwhelming do you guys plan to have a git repository or something?

Perfect! Thank you so much! And I just remembered that I can create a saved game for them with the preferences set up just as I like it and load it on their computers. Awesome!

This simple mod removes animals from the game: no animals.zip It's not the best solution, as it causes some error messages to pop up, but it works. To use it, simply unzip and past the folder inside 0.A.D\binaries\data\mods Then enable it in-game via options -> mod-selection

Hello! Thank you for the reply! I forgot about the whole texturing part of things and that is a whole other beast that I need to tackle and have 0 idea on how to tackle. I never understood texturing and still have a pretty rough time with it. Agh having no training in art makes this project pretty tough! I guess I'll eventually figure it out, at least I hope I will! I want to try looking at the animal blend files and go from there, maybe I can Frankenstein something together! Might look kind of freaky though lol... I'll keep all this in mind though, so much to learn! I need to find more people to work with me on this lol, one man isn't going to cut it I think! If there is anyone reading this who would like to help please message me !

Hello!! It has been some time since I've replied here, so I apologize if that is problematic! But I guess I just wanted to give an update on the progress of the mod! I've been slowly working on it though don't have much to show unfortunately. I am still figuring it out but its all making sense the more I work on it, though the endless folders are quite confusing. So far I've managed to make one of the maps that'll be apart of the mod and I've been crawling my way through the first factions units. Without a 3D artist though it has been kind of hard though since I can't really visualize everything and finding one has been impossible. I ended up taking the 3D modeling into my own hands since I do have some experience though I have no clue how to make something for a game. I've just been sticking to what I've noticed in the 0 AD models in that they don't have a whole lot of geometry which is nice! Kind of makes things easier! The only thing that I am wondering how to tackle is creating the non-humans, I have little confidence in my ability to put together something that looks proportionally correct and believable. So far I've only modeled a handful of the weapons in the mod. Here is what they look like! https://imgur.com/a/rgHBfCZ I am wondering now though, how do I put these weapons into the game? I tried to follow it with the folder structure and what not but got super confused and turned around with how many folders I was going through and eventually set it aside. Thank you for reading! I hope you have a wonderful day!