poke.AI
poke-AI/poke.AI
An experimental AI project designed to play Pokémon Emerald by combining computer vision, SLAM-inspired mapping, frontier-based exploration, and Deep Q-learning.
Overview
poke.AI breaks down the complex open-world gameplay of Pokémon Emerald into modular subsystems rather than relying on a single end-to-end model. It utilizes a Convolutional Neural Network for object detection, an absolute-coordinate mapping system inspired by SLAM, a BFS-based frontier exploration algorithm for navigation, and Deep Q-Learning to master combat strategies.
Capabilities
- ▸Object detection using Keras RetinaNet
- ▸SLAM-inspired game world mapping and localization
- ▸Frontier-based exploration and pathfinding with BFS
- ▸Deep Q-Learning for Pokémon battle optimization
Best for
Autonomous navigation and mapping of game environments, Object detection for in-game entities like NPCs and buildings, Reinforcement learning training for turn-based combat systems
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
This skill interacts with the desktop UI and emulator via automation tools like PyAutoGUI, which requires careful sandbox management if run on production or personal host machines.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.