HF RL Explorer

Sometimes experiement steps are skipped (e.g.

Sometimes experiement steps are skipped (e.g.: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). skip a charge if you're already at that voltage). When this happens the solver returns an EmptySolution. The next step of the experiment then starts from the wrong point. Steps to…

The task

skip a charge if you're already at that voltage). When this happens the solver returns an EmptySolution. The next step of the experiment then starts from the wrong point. Steps to Reproduce !image Relevant log output _No response_

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