Skip to content

LAV2_navrl

rsl-rl config for LAV2 NavRL with sensor-fusion policy.

Mirrors lav2/runner/skrl/cfg/LAV2_navrl.py but adapted to rsl-rl v5 native dict format. Uses :class:~lav2.runner.rsl_rl.models.navrl.SensorFusionMLPModel as the actor model class.

Usage (Isaac Lab Hydra entry point)::

"rsl_rl_cfg_entry_point": "lav2.runner.rsl_rl.cfg.LAV2_navrl:LAV2NavRLPPORunnerCfg"

Usage (direct script)::

from lav2.runner.rsl_rl.cfg.LAV2_navrl import get_runner_cfg
cfg = get_runner_cfg(experiment_name="my_run")
runner = OnPolicyRunner(env, cfg, log_dir, device=device)

Classes:

Name Description
BetaDistributionCfg

Configuration for the Beta output distribution.
LAV2NavRLPPORunnerCfg

Hydra-compatible config class for the NavRL task.

Functions:

Name Description
get_runner_cfg

Return a rsl-rl v5 native config dict for the NavRL task.

BetaDistributionCfg

Configuration for the Beta output distribution.

LAV2NavRLPPORunnerCfg

Bases: RslRlOnPolicyRunnerCfg

Hydra-compatible config class for the NavRL task.

get_runner_cfg 

get_runner_cfg(experiment_name: str = _EXPERIMENT_NAME, max_iterations: int = _MAX_ITERATIONS, lidar_out_dim: int = 128, dyn_obs_out_dim: int = 64, init_std: float = 1.0, distribution: str = 'beta', action_range: tuple[float, float] = (-1.0, 1.0)) -> dict

Return a rsl-rl v5 native config dict for the NavRL task.

Parameters:

Name Type Description Default

experiment_name

str

Logging directory name.

 _EXPERIMENT_NAME

max_iterations

int

Number of PPO iterations.

 _MAX_ITERATIONS

lidar_out_dim

int

Output dimension of the LiDAR CNN encoder.

 128

dyn_obs_out_dim

int

Output dimension of the dynamic-obstacle encoder.

 64

init_std

float

Initial standard deviation (Gaussian only). Default 1.0 (matches skrl NavRL config log_std=0).

 1.0

distribution

str

Output distribution, "beta" or "gaussian". Default "beta".

 'beta'

action_range

tuple[float, float]

Action space bounds (Beta only). Default (-1.0, 1.0).

 (-1.0, 1.0)