HF RL Explorer

I want a stateful SixMonthCycle Agent(window size: int, small: int, large: int, signal: int, up: float…

I want a stateful SixMonthCycle Agent(window size: int, small: int, large: int, signal: int, up: float…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). I want a stateful SixMonthCycle Agent(window size: int, small: int, large: int, signal: int, up: float, down: float)…

The task

I want a stateful SixMonthCycle_Agent(window_size: int, small: int, large: int, signal: int, up: float, down: float) strategy class that consumes prices and calendar dates one tick at a time. Its public step(price, date: str) -> int method should append the price to the agent's…

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