AI Research 技术调研

标签: rl-finetuning

此标签下有2条笔记。

  • 2026年7月16日

    DPPO: Diffusion Policy Policy Optimization

    • manipulation
    • diffusion-policy
    • reinforcement-learning
    • ppo
    • policy-gradient
    • rl-finetuning
    • sim-to-real
    • action-chunking
    • ddim
    • embodied-ai
  • 2026年7月16日

    ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

    • flow-matching
    • rectified-flow
    • shortcut-models
    • reinforcement-learning
    • ppo
    • policy-gradient
    • rl-finetuning
    • action-chunking
    • noise-injection
    • embodied-ai

  • GitHub