Teaching a simulated fighter martial arts with reinforcement learning, judged by a Muay Thai coach.https://ai.kakuto.io/https://ai.kakuto.io/blog/training-on-a-rented-gpu/https://ai.kakuto.io/blog/training-on-a-rented-gpu/Spot CPU machines on EC2 were getting expensive. Moving the fighter's physics onto a GPU, tuning the code for it and trying nine graphics cards cut the cost of training the stance by about 4.5 times.Wed, 21 Oct 2026 07:54:00 GMThttps://ai.kakuto.io/blog/learning-to-block/https://ai.kakuto.io/blog/learning-to-block/Twenty runs taught the fighter four Muay Thai blocks, then to watch an opponent and pick the right one. Four times it found a giveaway in the opponent instead of reading the punch.Tue, 20 Oct 2026 17:43:00 GMThttps://ai.kakuto.io/blog/walking-in-the-stance/https://ai.kakuto.io/blog/walking-in-the-stance/Twenty-two runs taught the fighter to step forward, back, sideways and diagonally, and to pivot, without forgetting its punches. Then every rule about how the walk should look made it walk worse.Mon, 19 Oct 2026 15:44:00 GMThttps://ai.kakuto.io/blog/faster-punches/https://ai.kakuto.io/blog/faster-punches/The five punches landed, but at an ordinary person's pace. Seven runs, a policy that sets its own timing, and a stronger elbow brought every punch to the target sooner, and finally landed the cross.Sun, 18 Oct 2026 16:27:00 GMThttps://ai.kakuto.io/blog/five-punches/https://ai.kakuto.io/blog/five-punches/Adding four punches to the jab, then air, pads and a heavy bag: ten training runs, a coach's corrections, and a fighter that now throws a near-human combination.Sun, 18 Oct 2026 10:00:00 GMThttps://ai.kakuto.io/blog/teaching-the-jab/https://ai.kakuto.io/blog/teaching-the-jab/Teaching a simulated fighter to jab: why a punch copied from an animation doesn't survive physics, and how each fix moved the problem somewhere else.Sun, 18 Oct 2026 00:00:00 GMThttps://ai.kakuto.io/blog/coaching-an-ai-fighter/https://ai.kakuto.io/blog/coaching-an-ai-fighter/A Muay Thai coach on teaching a simulated fighter to punch: why it is so much like teaching a person, and how he does it from his phone.Sat, 17 Oct 2026 00:00:00 GMThttps://ai.kakuto.io/blog/learning-to-balance-in-a-muay-thai-stance/https://ai.kakuto.io/blog/learning-to-balance-in-a-muay-thai-stance/How a simulated humanoid learned a coach-specified Muay Thai stance, then learned to take shoves of up to 860 N without falling and with its guard up.Fri, 16 Oct 2026 00:00:00 GMT