News for hackers. Stuff that matters.

A comment on 0 A.D. Alpha 25: Yaunā.

Re:0 A.D. Alpha 25: Yaunā by cl42 on Sunday August 08, 2021 @01:08PM (#28108242)
This game is awesome. I also love that they have support for reinforcement learning[1]. I wish all the research in RL and video games was on open source games. Slight bias on my end. :)

[1] https://trac.wildfiregames.com/wiki/GettingStartedReinforcem...

[ Parent | on HN ]
Re:0 A.D. Alpha 25: Yaunā by jonbaer on Sunday August 08, 2021 @01:49PM (#28108580)
What I am hoping to see is the Petra AI code stubbed out for ML/RL tasks, https://github.com/0ad/0ad/tree/master/binaries/data/mods/pu... ... nearly every manager/function there could have it's actions modified based on what it views or calculates in previous gameplay. One was introduced a few alphas back before the interface, https://github.com/agentx-cgn/Hannibal
[ Parent | on HN ]