alphaXiv/es-grpo-results download history
alphaXiv/es-grpo-results is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 312 times (12 in the last 7 days), and 1,013 times in total. It ranks #47,620 among datasets by monthly downloads.
ES vs GRPO: Evaluation Results Overview This repository contains comprehensive evaluation results comparing Evolution Strategies (ES) and Group Relative Policy Optimization (GRPO) on mathematical reasoning tasks. Tasks GSM8K: Grade school math word problems Countdow