Search Results for "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.
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.
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.
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.
NVIDIA's ProRL v2 Advances LLM Reinforcement Learning with Extended Training
NVIDIA unveils ProRL v2, a significant leap in reinforcement learning for large language models (LLMs), enhancing performance through extended training and innovative algorithms.
TorchForge RL Pipelines Now Operable on Together AI's Cloud
Together AI introduces TorchForge RL pipelines on its cloud platform, enhancing distributed training and sandboxed environments with a BlackJack training demo.
Leveraging Reinforcement Learning for Scientific AI Agents
Explore how reinforcement learning enhances scientific AI agents, reducing the burden of repetitive tasks and fostering innovation, as detailed by NVIDIA.
NVIDIA Unveils AI Agent Training Method Using Synthetic Data and GRPO
NVIDIA's new approach combines synthetic data generation with reinforcement learning to train CLI agents on a single GPU, cutting training time from months to days.
SkyRL Adds Vision-Language RL Support for Multimodal Models
SkyRL introduces vision-language reinforcement learning, enabling scalable training for multimodal tasks. Learn how this impacts AI development.
Machine Learning Network Fetch.ai Shares Vision of Interoperable Blockchains
Fetch.ai has a vision: to bring machine learning services to every ledger and blockchain.
Ethereum’s Medalla Experiences Critical Bug, but Prysmatic Labs Says ETH 2.0 Launch Is Unaffected
One of the top client teams staking on Ethereum 2.0 testnet announced that the crash that recently occurred was a learning experience and was salvaged.
CoinMarketCap Introduces Algorithmically Ranked Crypto Trading Pairs to Eradicate Volume Inflation
CoinMarketCap, a leading crypto data tracker, has gone a notch higher by presenting a new ranking system based on an innovative algorithm powered by machine learning. According to the company’s blog post, this new approach will enable users to make more profound trading decisions when it comes to market pairs. The new approach presented by CoinMarketCap seeks to revamp its current single metric ranking network to a combined one that will handle at least 22,000 market pairs covering more than 5,500 cryptocurrencies.
