QuantHive / openenv.yaml
ARKAISW's picture
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs
9cb3002
# OpenEnv Manifesto
version: "1.0"
name: "QuantHive"
description: "Decentralized multi-agent trading governance — three independent RL agents (Risk Manager, Portfolio Manager, Trader) with adversarial rewards negotiate via PettingZoo AEC turns."
author: "Arka Sarkar"
# Environment Specification
environment:
entry_point: "env.multi_agent_env:MultiAgentTradingEnv"
type: "pettingzoo_aec"
agents:
- risk_manager_0
- portfolio_manager_0
- trader_0
observation_space:
risk_manager_0: { shape: [24], dtype: "float32", description: "Market + portfolio + risk state" }
portfolio_manager_0: { shape: [27], dtype: "float32", description: "Base obs + RM constraints [size_limit, allow_new, force_reduce]" }
trader_0: { shape: [29], dtype: "float32", description: "Base obs + RM constraints + PM allocation [cap_alloc, override_strength]" }
action_space:
risk_manager_0:
type: "box"
shape: [3]
description: "[size_limit (0-1), allow_new_positions (0-1), force_reduce (0-1)]"
portfolio_manager_0:
type: "box"
shape: [2]
description: "[capital_allocation (0-1), override_strength (0-1)]"
trader_0:
type: "dict"
items:
direction: { type: "int", low: 0, high: 2, description: "0=Hold, 1=Buy, 2=Sell" }
size: { type: "float", low: 0.0, high: 1.0 }
sl: { type: "float", description: "Stop Loss price" }
tp: { type: "float", description: "Take Profit price" }
server:
port: 7860
endpoints:
reset: "/reset"
step: "/step"
state: "/state"
tags:
- "PettingZoo AEC"
- "Multi-Agent"
- "Adversarial Rewards"
- "Financial Governance"
- "Inter-Agent Negotiation"
- "Self-Regulation"