chenlin/Mujoco_WASM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update typos in sysid/README.md

Browse Source 
PiperOrigin-RevId: 868690171
Change-Id: Iffc71fb7bad73e18be767429600936014095ed9e
This commit is contained in:
Google DeepMind
2026-02-11 08:25:18 -08:00
committed by Copybara-Service
parent e9de358bfc
commit cc5d544d15
1 changed files with 7 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/mujoco/sysid/README.md
+7 -8
View File
@@ -17,14 +17,13 @@ across threads.
**You provide:** **You provide:**
- One or more `ModelSequences` each bundling a single `MjSpec` with one or - One or more `ModelSequences` each bundling a single `MjSpec` with one or
more sequences of measured data. All will be optimized jointly. more sequences of measured data. All will be optimized jointly.
- A `ParameterDict` defining differentiable `Parameter`'s with bounds. - A `ParameterDict` defining differentiable `Parameter`s with bounds.
- Callbacks to apply `Parameter`'s to an `MjSpec` (individually or jointly) - Callbacks to apply `Parameter`s to an `MjSpec` (individually or jointly)
- (optional) Functions (`build_model`, `custom_rollout`, `modify_residual`) - (optional) Functions (`build_model`, `custom_rollout`, `modify_residual`)
that override the default residual function behaviour. that override the default residual function behavior.
**The framework:** **The framework:**
- `build_residual_fn` which composes user code in `ModelSequences` and overrides - Composes user code into a residual function (`build_residual_fn`).
- Optimizes (`optimize`) the residual function returned by `build_residual_fn`
- Optimizes parameters via batched parallel rollouts (`optimize`). - Optimizes parameters via batched parallel rollouts (`optimize`).
- Saves results and generates an HTML report (`save_results`, `default_report`). - Saves results and generates an HTML report (`save_results`, `default_report`).
@@ -34,7 +33,7 @@ You can optimize any parameter that differentiably modifies the final
residuals. Common use cases include: residuals. Common use cases include:
**Physics parameters** settable on `MjSpec`. Most parameters in MjSpec **Physics parameters** settable on `MjSpec`. Most parameters in MjSpec
can be easily set directly by the user provided callbacks: can be easily set directly by user-provided callbacks:
| Target | Approach | | Target | Approach |
|---|---| |---|---|
@@ -42,7 +41,7 @@ can be easily set directly by the user provided callbacks:
| Joint damping | `spec.joint("j1").damping = p.value[0]` | | Joint damping | `spec.joint("j1").damping = p.value[0]` |
Convenience functions are provided for common system identification Convenience functions are provided for common system identification
parameterizations that cannot be trivially appled to an MjSpec: parameterizations that cannot be trivially applied to an MjSpec:
| Target | Approach | | Target | Approach |
|---|---| |---|---|
@@ -58,7 +57,7 @@ guaranteeing physical consistency without singularities.
**Measurement parameters** such as sensor delays, gains, and biases are **Measurement parameters** such as sensor delays, gains, and biases are
properties of the measurement system, not the physics model. The library properties of the measurement system, not the physics model. The library
provides utilities for applying these corrections to the residual after provides utilities for applying these corrections to the residual after
rollout, they are functionally complete but their API is not yet final. rollout. They are functionally complete but their API is not yet final.
## Example ## Example