| --- |
| tags: |
| - embodichain |
| - reinforcement-learning |
| - locomotion |
| --- |
| |
| # EmbodiChain models |
|
|
| Pretrained model bundles for [EmbodiChain](https://github.com/DexForce/EmbodiChain). |
| This repository contains 12 PPO policies: ANYmal-C, G1 flat locomotion, Go1, Go2, |
| H1_2 and MicroDuck, each with `default` and `newton` physics configurations. |
| |
| - [Model index](index.json): model IDs, tasks and tested runtime information. |
| - `policies/<model-id>/`: weights, RunManifest, configuration snapshots and evaluation evidence. |
| - [Policy evaluation documentation](https://github.com/DexForce/EmbodiChain/blob/main/docs/source/guides/cli.md#policy-evaluation): installation prerequisites, commands and options are maintained in EmbodiChain. |
| - Robot assets are distributed separately in `DexForceAI/embodichain_data`. |
|
|
| HF revisions version the index and bundles together. No videos are included. |
|
|
| ## Evaluation and licensing |
|
|
| No weight license is currently declared. EmbodiChain's code license does not |
| establish the redistribution terms of these weights. |
|
|
| All 12 policies completed 1,000 control steps (20 simulated seconds) with |
| FastRT using the public DexSim 0.5.0 wheel, Warp 1.15.0 and Newton 1.4.0. |
| Robot assets were downloaded through the standard resolver into a new cache. |
| G1 was also evaluated headlessly on both backends, starting with empty model |
| and asset caches. Checkpoint training counters and runtime versions are |
| recorded in each evaluation.json. |
|
|
| The evaluation used EmbodiChain main at `1b23ea0a` with the proposed pretrained |
| download entry point. Automatic `--pretrained` support is being prepared for |
| EmbodiChain; the bundles already use its existing native RUN layout. |
|
|
