DreamLake

RL logging on DreamLake

Record a complete, synthetic PPO / HalfCheetah experiment with the dreamlake Python package and your existing DreamLake login. This example does not train a policy or require MuJoCo, PyTorch, a GPU or a worker. Its rewards, losses and hardware measurements marked mock are simulated; logger timing is observed.

This is the DreamLake-native path. The other examples in this section use the standalone ml_dash package and dash.ml; those are separate backends.

Run the example

Use an existing namespace in which you may create a project, or an existing project in which you may write. Install and log in with the DreamLake CLI:

bash
dl login

Download both files into one directory:

bash
curl -fLO https://docs.dreamlake.ai/examples/rl-logging/mock_rl_experiment.py
curl -fLO https://docs.dreamlake.ai/examples/rl-logging/rl-dashboard.dashrc
uv run --python 3.12 mock_rl_experiment.py --project my-workspace/rl-demo

Replace my-workspace/rl-demo with your namespace and project. The script pins dreamlake[video]==0.46.2 in its inline dependency metadata; uv installs those dependencies. Alternatively, install that package and run the script with Python 3.12. The Python source and dashboard file are the maintained example; the script uploads both its source and the dashboard to the run.

The default creates a unique run name. Use --seed for another trial and --updates to change its length. --run chooses an explicit name; opening the same prefix again reuses that run and can append more data, rather than giving you an independent trial.

For a local-only rehearsal:

bash
uv run --python 3.12 mock_rl_experiment.py --project demo/rl-demo --updates 3 --interval 0 --local-root ./rl-local

Local mode does not create a remote project. The script retains production runs for inspection; remove disposable test runs separately when finished.

Existing login and project creation

The high-level remote entry used by the script is:

python
from dreamlake import Experiment

with Experiment(
    prefix="my-workspace/rl-demo/ppo-seed42",
    url="https://api.dreamlake.ai",
    root=None,
    tags=["rl", "ppo", "mock"],
    metadata={"mock": True},
) as exp:
    exp.params.set(algorithm="PPO", seed=42)
    exp.metrics("train").log(global_step=8192, policy_loss=-0.1, value_loss=60.0)
    exp.logs.info("PPO update recorded")

With this remote Experiment entry, a project reported missing is created as private, using the signed-in person's namespace permissions. An existing project is reused. The SDK does not create a missing namespace or bypass an access refusal. root=None selects remote-only storage; omitting url instead selects local storage by default.

If you construct NativeConnection.from_login(...) yourself, opt into project creation with auto_create_project=True; that lower-level option defaults to false. An existing platform job has its own pinned run and broker connection: see workload credentials instead of replacing it with this standalone login example.

What gets recorded

DataContents at the default 60 updates
ParametersPPO hyperparameters, seed, environment dimensions, policy architecture, optimizer and evaluation settings
rollout metrics60 rows of episode returns, episode length and reward components
train metrics60 rows of policy/value loss, entropy, KL, clipping, learning rate, gradient norm and action standard deviation
eval metrics12 rows of evaluation returns and a custom success rate, defined as return at least 4000
system metrics60 rows of logger timing and explicitly simulated environment/GPU measurements
LogsStart, evaluation, a labelled mock warning and completion messages
Tracksrollout/state and rollout/action, 60 timestamped entries each, including observations, joint state, actions and termination flags
FilesConfig, runtime information, source, three mock checkpoint JSON files, best-checkpoint selection, summary JSON, evaluation CSV, README, PNG, MP4 and .dashrc

A metric group contains multiple fields: train is one group, while train.policy_loss and train.value_loss are different chart keys. These four groups contain 192 rows and 28 value fields, not four curves. The two Tracks are separate timestamped streams, not two metrics.

Checkpoints are labelled mock JSON and are not loadable policy weights. The preview is a synthetic animation, not a MuJoCo rendering. The best checkpoint uses file tags; tags and canonical Bindr membership are different things.

Dashboard configuration

The script writes rl-dashboard.dashrc into the run root as .dashrc. It requests one chart per value field and includes the uploaded image and video. Each metric group logs its own global_step, so each chart uses that group's explicit x key. Update counters and timestamps are axes/bookkeeping, not extra value charts.

The supplied file contains 28 line charts, one image grid and one video grid. The header keeps two evaluation summaries; those two numbers do not describe how many metrics were stored. See per-run dashboard configuration for the format and the difference from automatic selection.

For an existing run, upload the configuration under the exact name .dashrc:

bash
dl experiments runs files upload RUN_ID ./rl-dashboard.dashrc --name .dashrc --prefix / --content-type text/plain --namespace my-workspace --project rl-demo

Use CLI 0.118.1 or newer for native disk-backed file uploads. Inspect an existing run configuration before replacing it; do not create several competing .dashrc files. After an out-of-page write, refresh the run page so it reloads the file list. CLI operations are documented in the Experiments reference.

SDK file Bindr limitation

SDK 0.46.0 was observed to ignore bindrs=[...] on native high-level file uploads; the same missing forwarding remains in the inspected 0.46.2 source. Run-level Bindrs work. This example therefore uses file tags rather than claiming those uploads create file membership.

When canonical membership is needed, flush the upload, obtain the stored file ID, and use the explicit project API:

python
# project is an authenticated client's experiments.project(namespace, project).
project.bindrs.attach("file", file_id, name="best-policy", run_id=run_id)
membership = project.bindrs.list("file", file_id, run_id=run_id)

Read the membership back. An explicit attachment repairs that file's data; it does not mean the high-level SDK forwarding defect has been fixed.