predict_rollout
Simulate future latent states by applying a sequence of 2D acceleration actions to a starting latent, using a learned dynamics model without interacting with the real environment.
Instructions
Roll the learned latent dynamics forward from a latent over an action sequence.
Given a starting latent and a list of 2D acceleration actions, applies the predictor g step by step and returns the latent trajectory. This is the model imagining a future without touching the real environment.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"latent": "<latent>",
"actions": "<actions>"
},
"name": "predict_rollout"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| latent | Yes | ||
| actions | Yes |