LAV2_p2m

rsl-rl config for the LAV2 P2M task.

Mirrors ~/Code/P2M/scripts/train.py but adapted to rsl-rl v5 native dict format. Uses :class:~lav2.runner.rsl_rl.models.navrl.SensorFusionMLPModel as the actor/critic model class for LiDAR CNN + state fusion.

Usage (Isaac Lab Hydra entry point)::

"rsl_rl_cfg_entry_point": "lav2.runner.rsl_rl.cfg.LAV2_p2m:LAV2P2MPPORunnerCfg"

Usage (direct script)::

from lav2.runner.rsl_rl.cfg.LAV2_p2m 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.
GaussianDistributionCfg	Configuration for rsl-rl's Gaussian output distribution.
LAV2P2MPPORunnerCfg	Hydra-compatible config class for the P2M task.

Functions:

Name	Description
get_runner_cfg	Return a rsl-rl v5 native config dict for the P2M task.

BetaDistributionCfg

Configuration for the Beta output distribution.

GaussianDistributionCfg

Configuration for rsl-rl's Gaussian output distribution.

LAV2P2MPPORunnerCfg

Bases: RslRlOnPolicyRunnerCfg

Hydra-compatible config class for the P2M task.

get_runner_cfg

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

Return a rsl-rl v5 native config dict for the P2M 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
init_std	float	Initial Gaussian standard deviation. Default 1.0 matches P2M's actor_std = zeros followed by exp.	1.0
distribution	str	Output distribution, "gaussian" or "beta". Default "gaussian" to match P2M's original policy.	'gaussian'
action_range	tuple[float, float]	Action space bounds (Beta only). Default (-1.0, 1.0).	(-1.0, 1.0)