Should a genome keep what its network learned? Three ways to mix gradients into evolution
Three hybrid trainers ask whether evolution should discard learned weights, inherit them, or pool experience in one gradient learner.
Posts tagged “Platformers”
Lab notebook posts about “Platformers”.
Learning to read the level: replacing lucky jumps with a policy gradient
A failed champion sets the test: can a policy read unseen Skyline Run levels instead of replaying one lucky route?
Can a deterministic game teach a network to run the rooftops?
A deterministic engine becomes a browser AI lab—and measurement catches the environment changing before training begins.
Teaching the trainer: evolving the reward instead of tuning it
Evolve better rewards automatically: AutoRL searches training settings; PBT, or population-based training, copies and perturbs the best runs.
The jump that measurement corrected
Building the platformer's first playable slice: the measured jump values, and the level design that only measurement could fix.
Before I Built a Platformer: What I Studied and What I Kept
What I studied before building Skyline Run, what I kept once the game existed, and what the AI agents that built it got wrong.