Topic

Reinforcement Learning

Everything filed under Reinforcement Learning, newest first.

Showing 1–2 of 2 articles

  • Introducing Particle-1

    Particle launches with Particle-1, a model RL post-trained (rank-64 LoRA, GSPO, Cascade RL) on DeepSeek V4.1 Flash to solve software engineering tasks with about 45% fewer tokens. Across Terminal-Bench 2.1, ReactBench, ADE Bench and DeepSWE 1.1 it uses 28–52% fewer output tokens and costs 34–52% less per task than the base model at comparable pass rates; available now via the Particle API.

    Announcement · AI Models · Reinforcement Learning · AI Agents

    9 min · 2,166 words

  • Towards Universal Post-Training for Robotics

    Perry Dong and Chelsea Finn on why robotics RL differs from LLM RL, what EXPO-FT gets right and wrong, and what a universal post-training recipe for real-world robots still needs.

    Research · AI · Robotics · Machine Learning · Research

    15 min · 3,484 words