Actions, Inverse Dynamics, and Latent Actions › Key Parameters
Michael BrenndoerferJuly 2, 20262 min read
World Models HandbookAll chapters Part 6 of 12Learning World Models at Scale
Actions, Inverse Dynamics, and Latent Actions › Key ParametersOne section · Sections in this chapter7 / 10 ↓
Sections in this chapter10
Reading tools Definitions & inline links
Choose your expertise level to adjust how many terms are explained. Beginners see more tooltips, experts see fewer to maintain reading flow. Hover over underlined terms for instant definitions.
Article links
Make inline references clickable
The key parameters for the worked example are:
- dt (
0.1): The simulation timestep. It scales how velocity integrates into position and how force converts into a velocity change. - gamma (
0.93): The per-step velocity damping factor. It controls how quickly velocity decays and therefore how far past actions influence the current state. - Effective action rank (
1): The action matrix has a single independent control column, so its noiseless action map is injective. Adding independent action columns does not create ambiguity unless the resulting action map loses column rank. - latent_dim (
1): The dimensionality of the learned latent action. The bottleneck limits capacity, but even one dimension can encode target information instead of the physical action. - hidden (
64): The width of the encoder and decoder hidden layers. - learning rate (
1e-3): The Adam step size used to train the latent action model. - epochs (
500): The number of full-batch training passes over the transitions. - alpha (
1e-6for the IDM,1e-3for the probe): The Ridge regularization strength. Small values keep the fit close to an exact linear solution. - train fraction (
0.8): The share of complete trajectories assigned to training, with the remainder held out for evaluation.