Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Facebookresearch Habitat lab Get config HRL

From Leeroopedia
Knowledge Sources
Domains Configuration_Management, Hierarchical_RL
Last Updated 2026-02-15 02:00 GMT

Overview

Concrete function for composing hierarchical RL experiment configurations with skill definitions and high-level policy selection, provided by habitat-baselines.

Description

The same get_config function from habitat-baselines is used but with HRL-specific YAML configs (rl_hierarchical.yaml, rl_skill.yaml). These configs define the hierarchical_policy section including defined_skills mapping, high_level_policy settings, and skill checkpoint paths.

Usage

Called with HRL-specific config paths (e.g., rearrange/rl_hierarchical.yaml) and overrides for skill checkpoint paths and high-level policy selection.

Code Reference

Source Location

  • Repository: habitat-lab
  • File: habitat-baselines/habitat_baselines/config/default.py (function), habitat-baselines/habitat_baselines/config/rearrange/rl_hierarchical.yaml (HRL config)
  • Lines: L27-43 (get_config)

Signature

def get_config(
    config_path: str,
    overrides: Optional[List[str]] = None,
    configs_dir: str = _BASELINES_CFG_DIR,
) -> DictConfig:
    """
    Same function as standard get_config, but invoked with HRL config paths.
    """

Import

from habitat_baselines.config.default import get_config

I/O Contract

Inputs

Name Type Required Description
config_path str Yes HRL config path (e.g., rearrange/rl_hierarchical.yaml)
overrides Optional[List[str]] No Overrides for skill checkpoints, HL policy name, etc.

Outputs

Name Type Description
config DictConfig Config with habitat_baselines.rl.policy.hierarchical_policy section populated

Usage Examples

Load HRL Config

from habitat_baselines.config.default import get_config

config = get_config(
    config_path="rearrange/rl_hierarchical.yaml",
    overrides=[
        "habitat_baselines.rl.policy.hierarchical_policy.high_level_policy.name=hl_neural",
    ],
)

Related Pages

Implements Principle

Requires Environment

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment