skip to content
RELIQUARY
PLATFORM / REINFORCEMENT LEARNINGCOMING SOON

Train your model on what matters.

Bring your model, task environment and grading method. The planned workflow puts rollout generation, reinforcement learning and inspectable checkpoints in one place, with evidence behind each update.

ILLUSTRATIVE EXAMPLEPlanned RL run package
Model
Pinned starting checkpoint
Task
Environment + grader
Signal
Graded rollout groups
Output
Checkpoint + evaluation evidence

Planned deliverables. No customer RL run is active and no result is claimed.

01 / WHAT YOU GET

Keep the work behind every checkpoint.

Inspect the starting model, task contract and training setup alongside the resulting checkpoint. Evaluation is a separate output, so you can check what changed. This planned workflow does not guarantee improvement.

  • Training configuration
  • Checkpoint
  • Evaluation evidence
02 / HOW IT WORKS

From graded attempts to a new checkpoint.

  1. 01

    Define the task

    Choose a model revision. Define the task, expected answer and grading method in an environment.

  2. 02

    Build the training signal

    Generate several attempts at each task and grade the answers. Contrast between rewards provides a relative learning signal; verification is a separate check.

  3. 03

    Follow the evidence

    Inspect the planned run configuration, updates and checkpoints. Keep the evaluation setup with the result, so you can see what changed and how it was measured.

Find the learning signalIllustrative
Same task · different responses16 attempts / group

All fail

No reward contrast

Mixed

Useful reward contrast

All pass

No reward contrast
group_relativeContrast between outcomes
How to read the signal

Each dot is an example response: an outlined dot fails (reward 0), a filled dot passes (reward 1). Mixed rewards distinguish responses within a group. Identical rewards provide no group-relative contrast in this binary-reward example.

Illustrative groups, not live telemetry or the network group size. Reward contrast does not guarantee model improvement.
03 / SCOPE & PRICING

Built around your workload.

No customer RL price or launch date is announced. Share your model, tasks and evaluation requirements to help scope an upcoming workload.

Read the documentation Prepare tasks and rewards for RL
Starting model
A pinned model revision and a qualified runtime. Public subnet research is separate from customer-supplied models.
Task environment
The task, expected answer and grading method, so each reward has an inspectable basis.
Run envelope
Training method, limits, checkpoint cadence and evaluation requirements, reviewed before execution.
04 / AVAILABILITY

Customer RL is coming soon.

Custom RL execution is not publicly available. Public Subnet 81 research is a separate activity. You can register interest or prepare a draft; saving a draft does not launch training.

Join the RL waitlist

Tell us about your workload. Requesting access does not start a job, reserve compute or grant execution permission.

Explore the environment catalog