Marketplaces / wshobson/agents / llm-finetuning/grpo-rlvr-training

llm-finetuning/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 functions, or when a GRPO run diverges or reward-hacks.

skill · @ 46891e7

Supported tools: all tools

Install in kendex: kendex add --skill llm-finetuning/grpo-rlvr-training after subscribing to wshobson/agents.