direct mujoco rendererGPT-5.5
Codex- Held-out 分数
- -3.473
- Checkpoint
- #012
- 重跑
- 50 steps
Validation-selected checkpoint rerun in the original environment; case return -1.880.
MuJoCo · Core16
控制连续动作机械臂到达目标点。
这些证据属于论文时期实验,并不表示相关 package 当前仍然可用。
每张卡片都在原研究 Environment 中重跑 validation 选出的 checkpoint。
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.
在该 Environment 内分数越高越好;不同任务的原始 reward scale 不可比较。
-3.473-3.979-5.103-6.506-43.77