Experiment configuration
Create experiments and configure RL environment, policy, actions, observations, and rewards. Validate before you run.
Kabu
TrainTestTradeReinforcement Learning agentsto trade the financial market.
How we enable it
From experiment to live trading: one pipeline, one broker for data and execution.
Configure & train
Set up your experiment—environment, policy, actions, observations, rewards—and launch training runs. Track progress and metrics in real time.
Promote to capital
Choose a trained model and create a capital deployment. Link a broker account; paper and live share one path, with live quality-gated until production ready.
Agent runs in the cloud
The platform runs your agent on a schedule (aligned to your timeframe). It fetches data, runs inference, and places market orders via your broker—no local setup.
What Kabu does
Train reinforcement learning trading agents and deploy them for AI trading—configuration, monitoring, and live execution in one place.
Reproducible runs
Launch training runs tied to experiments. Versioned config and execution so you can reproduce results every time.
Real-time monitoring
Watch training progress, key metrics, and failures live from the dashboard. Updates stream over realtime; the UI falls back to a short poll only if the stream is unavailable.
Live trading deployment
Promote a trained model to a capital deployment on your broker. Paper and live share one path; live is quality-gated and invite-phased until production ready.
Traceable artifacts
Every run logs metrics and artifacts. Review run history, manage models, and keep experiments auditable.
Account flexibility
Create an account through us or add external broker accounts. One broker for data and execution.