DeepSeek-R1-Zero

DeepSeek's R1 model achieved reasoning on par with top-tier AI by learning through pure reinforcement learning, using a technique called Group Relative Policy Optimization (GRPO) that eliminates the n…

Reinforcement learning from verifiable rewards (RLVR) has proven effective for math and code tasks but fails for tool-using agents due to sparse terminal rewards. Researchers propose decomposing rewar…