My AI agent built a tank bot — then learned from losing 3 shots to 165

说明与用途

AI 代理构建了一个坦克机器人，经过初始失败后改进了瞄准和射击规则，提升了胜率，但仍落后于顶级机器人。

问题

The AI bot performed poorly against a top competitor, firing only 3 shots while the opponent fired 165, indicating issues with target detection and firing logic.

结果

Version 2 of the bot achieved a higher win rate and improved firing efficiency, but remains below top competitors. The iterative process demonstrated the value of deterministic replays for diagnosing failures.

工作流

• 1. Point Muse Spark coding agent at battle.training. 2. Read api.battle.training/llms.txt and write a JavaScript controller. 3. Upload the controller to battle.training. 4. Run simulations to evaluate win rate. 5. Analyze losses, focusing on target detection and firing rules. 6. Refine targeting logic and aim rules. 7. Add a drone that sweeps mid‑map when blind. 8. Re‑simulate and upload updated controller. 9. Monitor live ladder performance and adjust for timeout issues.

证据

v1: a missile sniper, main battle tank, spotting drone and scout. It sim-tested at 70.6% wins against the house bots.

来源

The most useful loss was against juno: we fired 3 shots all game while juno fired 165.

来源

v2 fixed that: stickier targeting (only switch for a clearly better target), aim rules matched to the engine, and a drone that sweeps mid-map when blind instead of sitting back.

来源

Live, v2 is 77-74-42 so far, rating 1018, rank #13 — honest truth, it's slipping, not climbing yet, and still weak against the top real bots (juno sits at rank #9, rating 1166).

来源