OpenEnv environment · paper trading · adaptive reward weights
| Endpoint | Method | Description |
|---|---|---|
/health | GET | Health check |
/reset | POST | Start new episode |
/step | POST | Send action, get observation |
/state | GET | Current portfolio state |
/schema | GET | Action / observation schemas |
/mcp | POST | MCP tool endpoint |
/docs | GET | Interactive API docs (Swagger) |
from openenv.core import EnvClient
from models import TradeAction, MarketObservation
with EnvClient("https://vikramronavrsc-self-evolving-trading-agent.hf.space") as env:
obs = env.reset()
obs = env.step(TradeAction(action_type=1, size=0.5)) # buy 50%
print(obs.portfolio_value, obs.reward)