R_plan: A MCTS Agent for Card Games

A Tale of Dynamic Programming (2022)

▲ 90Brajeshwar13 HN discussion
R_plan: A MCTS Agent for Card Games

This post introduces R_plan, an AI agent that uses Monte Carlo Tree Search to play a suit of cards. It explains how R_plan combines multiple sub-agents to evaluate game states and make decisions, offering a fresh take on applying MCTS to card games.

R_plan acts as a MCTS agent, combining agents for a suit of cards.
Read original →HN discussionRSS

HN discussion

13
  1. flashfaffe2

    Thanks for the refreshing reminder.

    This was one of my favourite topic at school but ended never used it in professional environment. However , I will definitely review the theory. Banach spaces and fix theorem were kind useful definition/tool but I always struggled to understand practical applications.

    Thanks for sharing the article

  2. inigyou

    I was pretty sure the "dynamic" in "dynamic programming" was used as a synonym for "awesome" and had nothing to do with system dynamics.

  3. blackmoonx

    Duck Tales

More from this day

2026-08-12