encode_observation
Encodes a 6D observation vector into a latent embedding for the JEPA world model, enabling downstream prediction and planning tools.
Instructions
Encode a 6D observation [x, y, vx, vy, goal_x, goal_y] into a latent vector.
Returns the latent embedding produced by the trained JEPA encoder. The latent is the space the world model predicts in; downstream tools operate on these latents rather than on raw observations.
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": {
"observation": "<observation>"
},
"name": "encode_observation"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| observation | Yes |