An LMM iteratively repairs a Flappy Bird level generator to reach a target score using RL playtrace feedback in text, image, or combined form.
Deep reinforcement learning at the edge of the statistical precipice
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models
An LMM iteratively repairs a Flappy Bird level generator to reach a target score using RL playtrace feedback in text, image, or combined form.