Verified record · from the answer index

grpo-rlvr-training

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward fun

skill:wshobson/agents/grpo-rlvr-training · published by wshobson · source repository