Fixes example RL Navigation training

exts/nav_tasks/config/extension.toml

@@ -1,7 +1,7 @@
 [package]
 
 # Note: Semantic Versioning is used: https://semver.org/
-version = "0.3.11"
+version = "0.3.12"
 
 # Description
 title = "IsaacLab Navigation RL Tasks"

exts/nav_tasks/docs/CHANGELOG.rst

@@ -1,6 +1,14 @@
 Changelog
 ---------
 
+0.3.12 (2025-08-23)
+~~~~~~~~~~~~~~~~~~
+
+Fixed
+^^^^^
+
+- Fixed example RL training action scale and offset in :class:`nav_tasks.configs.env_cfg_base.ActionsCfg` for the low level action.
+
 
 0.3.11 (2025-08-13)
 ~~~~~~~~~~~~~~~~~~

exts/nav_tasks/nav_tasks/configs/env_cfg_base.py

@@ -112,6 +112,9 @@ def __post_init__(self):
             self.front_zed_camera, IMAGE_SIZE_DOWNSAMPLE_FACTOR, IMAGE_SIZE_DOWNSAMPLE_FACTOR
         )
 
+        # turn off the self-collisions
+        self.robot.spawn.articulation_props.enabled_self_collisions = False
+
 
 ##
 # MDP settings
@@ -125,7 +128,7 @@ class ActionsCfg:
     velocity_command = mdp.NavigationSE2ActionCfg(
         asset_name="robot",
         low_level_action=mdp.JointPositionActionCfg(
-            asset_name="robot", joint_names=[".*"], scale=1.0, use_default_offset=False
+            asset_name="robot", joint_names=[".*"], scale=0.5, use_default_offset=True
         ),
         low_level_policy_file=ISAACLAB_NUCLEUS_DIR + "/Policies/ANYmal-C/HeightScan/policy.pt",
     )

scripts/nav_tasks/train.py

@@ -5,10 +5,11 @@
 
 # This file has been adapted from https://github.com/isaac-sim/IsaacLab/blob/main/scripts/reinforcement_learning/rsl_rl/train.py
 
-# Copyright (c) 2022-2025, The Isaac Lab Project Developers.
+# Copyright (c) 2022-2025, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
 # All rights reserved.
 #
 # SPDX-License-Identifier: BSD-3-Clause
+
 """Script to train RL agent with RSL-RL."""
 
 """Launch Isaac Sim Simulator first."""
@@ -29,11 +30,15 @@
 parser.add_argument("--video_interval", type=int, default=2000, help="Interval between video recordings (in steps).")
 parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
 parser.add_argument("--task", type=str, default=None, help="Name of the task.")
+parser.add_argument(
+    "--agent", type=str, default="rsl_rl_cfg_entry_point", help="Name of the RL agent configuration entry point."
+)
 parser.add_argument("--seed", type=int, default=None, help="Seed used for the environment")
 parser.add_argument("--max_iterations", type=int, default=None, help="RL Policy training iterations.")
 parser.add_argument(
     "--distributed", action="store_true", default=False, help="Run training with multiple GPUs or nodes."
 )
+parser.add_argument("--export_io_descriptors", action="store_true", default=False, help="Export IO descriptors.")
 # append RSL-RL cli arguments
 cli_args.add_rsl_rl_args(parser)
 # append AppLauncher cli args
@@ -81,6 +86,7 @@
 from datetime import datetime
 
 import isaaclab_tasks  # noqa: F401
+import omni
 from isaaclab.envs import (
     DirectMARLEnv,
     DirectMARLEnvCfg,
@@ -104,7 +110,7 @@
 torch.backends.cudnn.benchmark = False
 
 
-@hydra_task_config(args_cli.task, "rsl_rl_cfg_entry_point")
+@hydra_task_config(args_cli.task, args_cli.agent)
 def main(env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg, agent_cfg: RslRlOnPolicyRunnerCfg):
     """Train with RSL-RL agent."""
     # override configurations with non-hydra CLI arguments
@@ -141,6 +147,15 @@ def main(env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg, agen
         log_dir += f"_{agent_cfg.run_name}"
     log_dir = os.path.join(log_root_path, log_dir)
 
+    # set the IO descriptors output directory if requested
+    if isinstance(env_cfg, ManagerBasedRLEnvCfg):
+        env_cfg.export_io_descriptors = args_cli.export_io_descriptors
+        env_cfg.io_descriptors_output_dir = log_dir
+    else:
+        omni.log.warn(
+            "IO descriptors are only supported for manager based RL environments. No IO descriptors will be exported."
+        )
+
     # create isaac environment
     env = gym.make(args_cli.task, cfg=env_cfg, render_mode="rgb_array" if args_cli.video else None)