{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "muellerberndt-cadence--run-continuing-brain-on-live-feedback",
 "repo": "muellerberndt/cadence",
 "repo_url": "https://github.com/muellerberndt/cadence",
 "repo_slug": "muellerberndt-cadence",
 "title": "Run a continuing brain that learns from live rewards",
 "page_title": "How to run a continuing brain that learns from live rewards with Cadence",
 "summary": "Compose a System 1 brain and feed it observations and measured rewards in one ongoing stream.",
 "who": "A researcher or developer testing an agent that must keep learning as its environment changes, with no separate training and inference phases.",
 "problem": "Most learning setups split training from use, so an agent cannot keep adapting to a stream of outcomes in one continuing run.",
 "outcome": "A running brain that returns one action per observation, takes the previous action's reward on each call, and reports its settlement work.",
 "steps": [
  "`python -m pip install cadence-net==0.84.3`",
  "Create a Python file that runs `brain = Brain.compose(inputs=4, actions=2, arousal=True)` from `cadence`.",
  "Call `action = brain.live(observation)` with one observation row, execute the action in your environment, and measure the reward.",
  "Call `action = brain.live(next_observation, reward=reward)` for each following step, passing the reward of the preceding action.",
  "Read `brain.last_settlement` after each call to check residual, qualification and sweeps."
 ],
 "agent_prompt": "Using the Python package cadence-net (repo muellerberndt/cadence), write a loop that drives Brain.compose(inputs=4, actions=2, arousal=True) through live() calls on the toy environment at <environment file>. Expected output: a printed log of actions, rewards and last_settlement values for 200 steps. Verify that each call after the first passes the reward of the previous action.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "Cadence is alpha research software, so the first run tests the library's mechanisms rather than delivering a production controller.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.11 or newer",
  "NumPy installed through pip",
  "A toy environment or task that can supply an observation and a measured reward after each action"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/muellerberndt-cadence/run-continuing-brain-on-live-feedback/",
 "md": "https://dedupedai.com/use-cases/muellerberndt-cadence/run-continuing-brain-on-live-feedback/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/muellerberndt-cadence--run-continuing-brain-on-live-feedback.json",
 "api_version": "v1"
}