SUMMARY AI summary by gpt-5-mini
Blackjack-Agent is a Deep Q-Network implementation that learns a blackjack policy for the assignment in TASK.md. It models a clarified 52-card variant (reshuffle only when the draw pile is exhausted, up to five players, dealer hits to 17, actions: hit/stand/double with double only allowed as first action) and uses terminal rewards +1/0/-1 (doubled if doubled). The DQN takes an observable state vector and outputs Q-values for three actions. State features include player total, usable ace, dealer upcard, double legality, estimated remaining 52-card counts, visible opponent cards, and opponent count. Illegal actions are masked; rewards are sparse and only given at round end. Includes scripts to train (python -m scripts.train_dqn), evaluate, and a live_session helper for physical-card play that tracks seen cards. Checkpoints before the 52-card clarification must be retrained. Licensed under PolyForm Noncommercial 1.0.0.
Language breakdown (by bytes)
Owner
Dates
| Created on GitHub | 2026-05-08 |
| Last push | 2026-05-15 |
| First seen here | 2026-05-09 |
| Last fetched | 2026-05-16 18:12 |
Similar repos (same language)
Reverse proxy for your ai quota from the SW platform.
dea6cat/2b-agentThis llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus
Zuboy/Carbon-Cost-Optimizer-Agentic-AIAn AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.
FuchaZ/lm-studio-vision-bridge给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务
Shrutirowlo/AI-Video-AgentAI-powered video generation agent that automates script analysis, scene planning, and video creation.
Shivang0/social-visionPaste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.
markusbegerow/claude-fuer-oeffentliche-verwaltung⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.
knowledgegut/course-distiller把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF；最後的重組交還人腦。A Claude Code skill by 知識包小腸.