HF RL Explorer

bhoy/babyai-pure-objective-switches-200step

BabyAI Pure-Objective Switches (200 Steps): Verifiers environment on Hugging Face. This public archive contains four Qwen3.5-9B Prime-RL runs on the packaged AgentBoard BabyAI v1 environment:

bhoy/babyai-pure-objective-switches-200step on the Hugging Face Hub