HF RL Explorer

Repair River's online AdaBoost weighting and probability aggregation, then run deterministic prequential…

Repair River's online AdaBoost weighting and probability aggregation, then run deterministic prequential…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). Repair the online AdaBoost training path The vendored River source under /app/vendor/project contains a regression in…

The task

Repair the online AdaBoost training path The vendored River source under /app/vendor/project contains a regression in its online AdaBoost classifier. Repair the existing implementation and run the frozen streaming-training workflow. Required source repairs Modify both of these…

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