HF RL Explorer

Round-Robin GPU scheduling does not follow CUDA VISIBLE DEVICES spec

Round-Robin GPU scheduling does not follow CUDA VISIBLE DEVICES spec: a task in MiMo-V2.6-RL-harbor-code: MiMo-V2.6-RL Code (Harbor) (Harbor dataset). CUDA VISIBLE DEVICES: "RR1,3,5,7" works, but

The task

`CUDA_VISIBLE_DEVICES: "RR1,3,5,7"` works, but

Part of FineEnvs/MiMo-V2.6-RL-harbor-code.