Crushing Hearts with Deep CFR

Name: Crushing Hearts with Deep CFR
Availability: InStock
Author: brianberns

by brianberns·Mar 12, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidNiche GemBig Brain

Superhuman Hearts AI using Deep CFR, playable directly in the browser.

Strengths

•Deep CFR handles imperfect information better than traditional Minimax search trees.
•Browser-based demo allows immediate verification of the superhuman play claims.
•Clean UI makes complex game state and AI decisions easy to follow.

Weaknesses

•Niche appeal limits audience to game AI researchers and card game enthusiasts.
•Lacks benchmark data comparing performance against other established Hearts bots.

Post Description

I built a machine learning project to play the card game Hearts at a superhuman level.

Similar Projects

Open Source●Mid

Algorithms 1.0.0 – Minimal and clean implementations of algorithms

Files are single-purpose and readable: each algorithm comes with docstrings, type hints, complexity notes and runnable examples so you can read, test, or pip-install bits immediately. It isn't breaking new ground — algorithm collections are common — but the focus on clarity, tests, and a tiny surface API (merge_sort, BinaryHeap, dijkstra, etc.) makes this a reliable reference and teaching aid.

Niche GemCrowd Pleaser

kwk236

704mo ago

AI/ML●●●Banger