name: stocker
version: 0.1.0
description: >
  A stock-trading RL environment built on OpenEnv. Long-term backtest over
  3 historical episodes (AAPL, INTC, META). Per-step decisions are produced
  by a council of 7 LLM specialist agents (chart, seasonal/long-term, technical
  indicators, news, forum sentiment, peers + commodity, geopolitics/macro)
  whose votes are merged by a moderator LLM. The moderator is GRPO-trained
  via TRL on top of google/gemma-4-E4B-it.

tasks:
  - task_easy
  - task_medium
  - task_hard

observation_space:
  ticker: str
  date: str
  price: float
  price_history: "list[float]"
  fundamentals: dict
  cash: float
  position: int
  portfolio_value: float
  task_id: str
  step_number: int
  total_steps: int
  chart_path: str
  headlines: "list[dict]"
  forum_excerpts: "list[dict]"
  indicators: dict
  peers: dict
  macro: "list[dict]"

action_space:
  side: "literal[buy, sell, hold]"
  quantity: int

entrypoint: app.core.environment:StockerEnv

tags:
  - openenv
  - finance
  - trading
  - multi-agent
  - rl