Reinforcement Learning
Reinforcement Learning
NVIDIA NeMo-RL Utilizes GRPO for Advanced Reinforcement Learning
NVIDIA introduces NeMo-RL, an open-source library for reinforcement learning, enabling scalable training with GRPO and integration with Hugging Face models.
Reinforcement Learning
DeepSWE: Revolutionizing Coding Agents with Open-Source Reinforcement Learning
DeepSWE-Preview, an advanced coding agent, sets new benchmarks in open-source AI with a 59% success rate on SWE-Bench-Verified, showcasing state-of-the-art performance using reinforcement learning.
Reinforcement Learning
Exploring Open Source Reinforcement Learning Libraries for LLMs
An in-depth analysis of leading open-source reinforcement learning libraries for large language models, comparing frameworks like TRL, Verl, and RAGEN.
Reinforcement Learning
NVIDIA Unveils Llama 3.1-Nemotron-70B-Reward to Enhance AI Alignment with Human Preferences
NVIDIA introduces Llama 3.1-Nemotron-70B-Reward, a leading reward model that improves AI alignment with human preferences using RLHF, topping the RewardBench leaderboard.