Back to the work
AI/ML · Builder

Data Clean Env.

An OpenEnv-compliant reinforcement-learning environment for tabular data cleaning. An agent fixes messy datasets through a typed action space (convert types, fill missing, dedupe, standardize, parse dates) and is scored per issue resolved. Built for the Meta OpenEnv Hackathon.

Role
Builder
When
2026
Stack
Python, FastAPI, OpenEnv, Docker
Scale
4 tasks graded scenarios
View live demo ↗GitHub ↗
Data Clean Env previewOpenEnv · RL · data cleaning
4 tasksgraded scenarios
7 actionstyped action space
OpenEnvspec-compliant
score 0-1per-check reward

The problem

Data cleaning is the unglamorous core of data engineering, fixing types, nulls, duplicates, and inconsistent formatting, and it is exactly the kind of structured, checkable task an agent could learn. The problem was framing it as a reinforcement-learning environment: a clean action space, observations an agent can reason over, and a reward that rewards fixing real issues rather than just changing cells.

What it does

  1. An OpenEnv-compliant RL environment (built on the OpenEnv Action/Observation base types) so it plugs into the standard tooling rather than inventing its own protocol.
  2. A typed action space of seven cleaning operations: replace_value, convert_type, fill_missing, remove_duplicates, drop_rows, standardize (case/trim), and parse_date.
  3. Rich observations: the current data, per-column metadata (dtype, null counts, unique counts), a running quality score in [0, 1], and issues-fixed-versus-total progress, so the agent can see what is still wrong.
  4. Four graded tasks, from a 5-row type-fixing warm-up to a 15-row full-pipeline mix of every issue, served by a FastAPI app and packaged in Docker for deployment as a Space.

Impact

  • Turns a fuzzy chore into a checkable RL task: each fixed issue is worth a fraction of the score, so the reward tracks real data-quality improvement rather than activity.
  • OpenEnv compliance means the environment is interoperable with the standard client and inference tooling instead of being a one-off harness.
  • A reference client, inference format, and grader tests ship alongside, so the environment is runnable and verifiable, not just a description.