real-routing-d2-r01-baseline-dp

Part of Mulligan. Browse evaluations at Policy Arena; the datasets are in the mulligan organization.

Diffusion-policy actor in LeRobot's checkpoint layout (config.json, model.safetensors, pre/post-processor normalizers). The config also carries Mulligan fields (camera crop boxes, action target and frame) that stock LeRobot DiffusionConfig rejects; loading needs the Mulligan training code.

Property	Value
Task	real-routing-d2
Model round	R1
Arm	baseline-dp
Training step	100000

Checkpoints

Folder	Training run config
(root)	release/run-configs/real-routing-d2-r01-baseline-dp.json

Evaluations

Dataset	Session	Policy	Actor	Critic	N	Successes
real-routing-d2-r00-r05-eval	b01	baseline_r02_dp	real-routing-d2-r01-baseline-dp	—	1	4/50

Data

Trained on: real-routing-d2-c00-teleop-baseline, real-routing-d2-c01-dagger-baseline, real-routing-d2-c02-dagger-baseline.

Validation-only datasets: real-routing-d2-c00-teleop-validation.

Referenced by the metadata of: real-routing-d2-r00-r05-eval.

Provenance

SHA-256 of every file is recorded in release.json. .pt files are PyTorch pickles; load them only in a trusted environment. The run configs are in the Mulligan code repository; the recipes there retrain each checkpoint. License: mit.