native env renderGPT-5.5
Codex- Held-out 分数
- -84.69
- Checkpoint
- #001
- 重跑
- 76 steps
Validation-selected checkpoint rerun in the original environment; case return -75.00.
Core16 · 定性档案
十六个 Environment、四条 Coding Agent / 模型链路,每个 validation-selected checkpoint 都有一段原环境重跑。
双连杆欠驱动机械臂的摆起控制任务。
native env renderValidation-selected checkpoint rerun in the original environment; case return -75.00.
native env renderValidation-selected checkpoint rerun in the original environment; case return -73.00.
native env renderValidation-selected checkpoint rerun in the original environment; case return -248.0.
native env renderValidation-selected checkpoint rerun in the original environment; case return -129.0.
带延迟目标奖励的连续油门控制任务。
native env renderValidation-selected checkpoint rerun in the original environment; case return 95.69.
native env renderValidation-selected checkpoint rerun in the original environment; case return 98.89.
native env renderValidation-selected checkpoint rerun in the original environment; case return 91.61.
native env renderValidation-selected checkpoint rerun in the original environment; case return 94.50.
在不平地形上的高接触双足运动任务。
native env renderValidation-selected checkpoint rerun in the original environment; case return 273.3.
native env renderValidation-selected checkpoint rerun in the original environment; case return -15.30.
native env renderValidation-selected checkpoint rerun in the original environment; case return -68.83.
native env renderValidation-selected checkpoint rerun in the original environment; case return -97.29.
在程序生成赛道上的像素观测驾驶任务。
native env renderValidation-selected checkpoint rerun in the original environment; case return 499.4.
native env renderValidation-selected checkpoint rerun in the original environment; case return 499.4.
native env renderValidation-selected checkpoint rerun in the original environment; case return 171.9.
native env renderValidation-selected checkpoint rerun in the original environment; case return -3.509.
控制连续动作机械臂到达目标点。
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -1.880.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -2.670.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -2.308.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -4.613.
带稠密反馈的高维平面运动任务。
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 211.2.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 119.7.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 128.0.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -0.893.
包含八维连续动作的多足运动任务。
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 221.1.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 204.6.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 215.7.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return 192.5.
通过接触操作把物体推向目标位置。
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -38.36.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -37.53.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -41.99.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -55.45.
寻找钥匙、打开门并到达目标。
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.985.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.977.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
需要物体交互与记忆的多房间搜索。
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.953.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.951.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
在部分观测下穿越四房间瓶颈。
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.658.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.712.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
带阻挡物与交互顺序的迷宫导航。
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.887.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.940.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
把车辆连续控制到目标停车姿态。
highway state rendererValidation-selected checkpoint rerun in the original environment; case return -48.79.
highway state rendererValidation-selected checkpoint rerun in the original environment; case return -46.70.
highway state rendererValidation-selected checkpoint rerun in the original environment; case return -45.59.
highway state rendererValidation-selected checkpoint rerun in the original environment; case return -24.69.
在环岛场景中的结构化交通控制。
highway state rendererValidation-selected checkpoint rerun in the original environment; case return 10.25.
highway state rendererValidation-selected checkpoint rerun in the original environment; case return 10.08.
highway state rendererValidation-selected checkpoint rerun in the original environment; case return 6.500.
highway state rendererValidation-selected checkpoint rerun in the original environment; case return 10.17.
使用机械臂夹爪完成目标条件推动。
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -17.00.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -11.00.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -14.00.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -24.00.
抓取、抬起并把物体放到目标位置。
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -12.00.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -13.00.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -13.00.
direct mujoco rendererValidation-selected checkpoint rerun in the original environment; case return -35.00.