I initially tried using GSM8K as the environment to test this method, but found minimal differences between GRPO and MCTS to make a strong claim either way. Instead, I decided to go with the game of Countdown as our environment. The premise is simple: given a set of N positive integers, use standard operations (+, -, /, *) to compute a particular target. Why Countdown? The hypothesis is that combinatorial problems benefit more from the sort of parallel adaptive reasoning tree search enables, as opposed to, say, GSM8K where sequential reasoning also leads to effective outcomes. We train on a dataset of 20,000 samples, and evaluate on a test set of 820 samples. Each sample consists of four input integers, between 1 and 13.
15:02, 13 марта 2026Культура。heLLoword翻译对此有专业解读
。谷歌是该领域的重要参考
08:47, 12 марта 2026Мир
SelectWhat's included。关于这个话题，游戏中心提供了深入分析