HF RL Explorer

Inconsistency in numba mode when passing scalar to function

Inconsistency in numba mode when passing scalar to function: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). In numba mode: In c mode: This came up in https://github.com/pymc-devs/pymc/issues/5937. Found by bherwerth.

The task

In numba mode: In c mode: This came up in https://github.com/pymc-devs/pymc/issues/5937. Found by bherwerth.

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.