frFrançais

Yannic Kilcher

Name: Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning (Paper Explained)
Uploaded: 2020-05-08T13:10:29.000Z

I make videos about machine learning research papers, programming, and issues of the AI community, and the broader impact of AI in society.

Chaîne YouTube officielle ↗

Vidéos: 487
Abonnés: 333 k
Vues totales: 18,3 M
Dernières vidéos: 6 mars 2026

Page indépendante
Machine Learning
Langue du contenu: anglais
Région: Suisse

Cette page d'annuaire indépendante est gérée par Youtop. Elle n'est ni gérée, ni sponsorisée, ni approuvée par Yannic Kilcher ou par YouTube. Chaîne YouTube officielle ↗Suggérer une correction Vous êtes ce créateur ? Revendiquez cette page

Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning (Paper Explained) — Yannic Kilcher · Youtop

Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning (Paper Explained)

Yannic Kilcher · Publiée le 8 mai 2020

Regarder sur YouTube ↗

D'après les métadonnées YouTube

When AI makes a plan it usually does so step by step, forward in time. But often it is beneficial to define intermediate goals to divide a large problem into easier sub-problems. This paper proposes a generalization of MCTS that searches not for the best next actions to take, but for the best way to sub-divide the problem recursively into problems so tiny that they can each be solved in a single step. Paper: https://arxiv.org/abs/2004.11410 Site: https://sites.google.com/view/dc-mcts/home Abstract: Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed. We consider alternatives to this assumption for the class of goal-directed Reinforcement Learning (RL) problems. Instead of an environment transition model, we assume an imperfect, goal-directed policy. This low-level policy can be improved by a plan, consisting of an appropriate sequence of sub-goals that guide it from the start to the goal state. We propose a planning algorithm, Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS), for approximating the optimal plan by means of proposing intermediate sub-goals which hierarchically partition the initial tasks into simpler ones that are then solved independently and recursively. The algorithm critically makes use of a learned sub-goal proposal for finding appropriate partitions trees of new tasks based on prior experience. Different strategies for learning sub-goal proposals give rise to different planning strategies that strictly generalize sequential planning. We show that this algorithmic flexibility over planning order leads to improved results in navigation tasks in grid-worlds as well as in challenging continuous control environments. Authors: Giambattista Parascandolo, Lars Buesing, Josh Merel, Leonard Hasenclever, John Aslanides, Jessica B. Hamrick, Nicolas Heess, Alexander Neitz, Theophane Weber Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://www.bitchute.com/channel/yannic-kilcher Minds: https://www.minds.com/ykilcher

Plus de Yannic Kilcher

Tout voir

13:46I BUILT A FULLY AUTOMATIC MANSPLAINER6 mars 2026

Direct2:33:37Traditional X-Mas Stream29 déc. 2025

Direct0:00Traditional Holiday Live Stream28 déc. 2025

← Retour à Yannic Kilcher