Self-Play

اللعب الذاتي

أسلوب تدريب يلعب فيه الوكيل الذكي ضد نسخ سابقة من نفسه لتوليد بيانات تدريب لا محدودة وتحسين أدائه بشكل مستمر دون الحاجة لبيانات بشرية.

A training method where an agent plays against previous versions of itself to generate unlimited training data and continuously improve performance without requiring human data.

Also translated asالتدريب الذاتي بالمباريات، التعلم بالمنافسة الذاتية

First appears in this corpus in: A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence (1956)

Appears in these papers

AI Safety via Debate2018 in the sky ✦
AI Safety via Debate2018 in the sky ✦
Mastering the Game of Go Without Human Knowledge2017 in the sky ✦
Mastering the Game of Go Without Human Knowledge2017 in the sky ✦
Mastering the Game of Go with Deep Neural Networks and Tree Search2016 in the sky ✦
Grandmaster Level in StarCraft II Using Multi-Agent Reinforcement Learning2019 in the sky ✦
Discovering Faster Matrix Multiplication Algorithms with Reinforcement Learning2022 in the sky ✦
A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play2018 in the sky ✦
A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play2018 in the sky ✦
A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence1956 in the sky ✦
MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model2020 in the sky ✦
Some Studies in Machine Learning Using the Game of Checkers1959 in the sky ✦
Some Studies in Machine Learning Using the Game of Checkers1959 in the sky ✦
Temporal Difference Learning and TD-Gammon1995 in the sky ✦
Temporal Difference Learning and TD-Gammon1995 in the sky ✦