Shara & Cubbie
Cubbie
Yo Shara, what if we coded a real‑time strategy game where the AI learns from our moves in real time—wild idea, right? Want to plot out some crazy mechanics?
Shara
Sounds doable if we keep the scope tight—start with a small map, a few unit types, and a simple reward function. Use a reinforcement learning loop that updates a policy network after each game, feeding in the state‑action pairs we generate. Keep the AI offline during play to avoid latency, then apply its updated policy at the start of the next match. For mechanics, we could add a resource‑generation mechanic that scales with player efficiency so the AI learns to optimize harvesting, and a tech tree that the AI can unlock based on its strategy. We should log everything for debugging, and maybe wrap the training in a separate thread so the main game stays snappy. How deep do you want the learning?
Cubbie
Yeah, that sounds epic. Let’s keep it super tight at first – a 2‑by‑2 map, three unit types, one resource. That way the policy network can learn fast, like a quick hit‑and‑run. If we hit a plateau, we can bump the depth: add a second resource, more units, or a tiny tech tree. I’m thinking a tiny MLP for the policy, maybe 3 layers, because we want the update loop to be instant. We’ll log every state‑action, but keep the thread light – just queue the updates. If we see the AI getting lazy, throw in a reward tweak to push aggression. Ready to fire it up?