A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Sign Up to like & getrecommendations! Published in 2018 at "Science"
DOI: 10.1126/science.aar6404
Abstract: One program to rule them all Computers can beat humans at increasingly complex games, including chess and Go. However, these programs are typically constructed for a particular game, exploiting its properties, such as the symmetries… read more here.
Keywords: self play; game; chess shogi; reinforcement learning ... See more keywords
ExSPIN: Explicit Feedback-Based Self-Play Fine-Tuning for Text-to-SQL Parsing
Sign Up to like & getrecommendations! Published in 2025 at "Entropy"
DOI: 10.3390/e27030235
Abstract: Recently, self-play fine-tuning (SPIN) has garnered widespread attention as it enables large language models (LLMs) to iteratively enhance their capabilities through simulated interactions with themselves, transforming a weak LLM into a strong one. However, applying… read more here.
Keywords: play fine; text sql; language; self play ... See more keywords
Efficient Parallel Design for Self-Play in Two-Player Zero-Sum Games
Sign Up to like & getrecommendations! Published in 2025 at "Symmetry"
DOI: 10.3390/sym17020250
Abstract: Self-play methods have achieved remarkable success in two-player zero-sum games, attaining superhuman performance in many complex game domains. Parallelizing learners is a feasible approach to handle complex games. However, parallelizing learners often leads to the… read more here.
Keywords: zero sum; two player; player zero; self play ... See more keywords