plan_to_goal
Plans the next action to reach a goal by encoding current and goal observations, searching action sequences via latent MPC, and returning the first action of the best plan. Replan each step for receding-horizon control.
Instructions
Plan the next action that drives the agent toward a goal, via latent MPC.
Encodes the current and goal observations, searches action sequences by rolling the world model forward in latent space (cross-entropy method), and returns the first action of the best plan. Call repeatedly (replanning each step) to follow a receding-horizon trajectory to the goal.
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": {
"current_obs": "<current_obs>",
"goal_obs": "<goal_obs>"
},
"name": "plan_to_goal"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| current_obs | Yes | ||
| goal_obs | Yes |