AI Research 技术调研

标签: hierarchical-rl

此标签下有5条笔记。

  • 2026年7月16日

    ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots

    • legged-locomotion
    • quadruped
    • anymal
    • parkour
    • hierarchical-rl
    • sim-to-real
    • terrain-reconstruction
    • navigation
    • perception
    • isaac-gym
  • 2026年7月16日

    HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation

    • embodied-ai
    • benchmark
    • humanoid
    • whole-body-control
    • loco-manipulation
    • mujoco
    • unitree-h1
    • dexterous-hands
    • hierarchical-rl
    • tactile
  • 2026年7月16日

    SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending

    • humanoid
    • whole-body-control
    • loco-manipulation
    • hierarchical-rl
    • skill-blending
    • goal-conditioned
    • cross-embodiment
    • benchmark
    • reward-hacking
    • isaac-gym
  • 2026年7月16日

    Model-based Reinforcement Learning: A Survey

    • model-based-rl
    • planning
    • survey
    • taxonomy
    • dyna
    • muzero
    • alphago-zero
    • implicit-model-based-rl
    • exploration
    • hierarchical-rl
  • 2026年7月16日

    Deep Hierarchical Planning from Pixels (Director)

    • world-model
    • hierarchical-rl
    • feudal-rl
    • model-based-rl
    • rssm
    • goal-conditioned
    • latent-imagination
    • sparse-reward
    • quadruped-navigation
    • atari

  • GitHub