[tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor

[Viru97]

Hello Guys,

I get following error mid rl training, I am new to reinforcement learning. I have no idea how to solve this.
Any suggestions. Thank you!

I tried:

1. Reducing physics time step
2. increasing solver_position_iteration_count,
   solver_velocity_iteration_count,

ROBOT_CFG = ArticulationCfg(
        spawn=sim_utils.UsdFileCfg(
            usd_path=''
            rigid_props=sim_utils.RigidBodyPropertiesCfg(
                disable_gravity=True,
                max_depenetration_velocity=5.0,
                solver_position_iteration_count=64,
                solver_velocity_iteration_count=4,
            ),
        ),
        init_state=ArticulationCfg.InitialStateCfg(
            joint_pos={
                "shoulder_pan_joint": 0.0, "shoulder_lift_joint": -2.62, "elbow_joint":2.1,
                "wrist_1_joint":-2.1, "wrist_2_joint":-1.57, "wrist_3_joint":3.14}
        ),
        actuators = {
                        "arm": ImplicitActuatorCfg(
                            joint_names_expr=["shoulder_pan_joint", "shoulder_lift_joint", "elbow_joint",
                                              "wrist_1_joint", "wrist_2_joint", "wrist_3_joint"],
                            velocity_limit=20.0,
                            effort_limit=87.0,
                            stiffness=800.0,
                            damping=40.0,
                        ),
                        "hand": ImplicitActuatorCfg(
                            joint_names_expr=['right_index_1_joint', 'right_middle_1_joint',
                             'right_little_1_joint', 'right_ring_1_joint', 'right_thumb_1_joint', 'right_thumb_2_joint'],
                            velocity_limit=20.0,
                            effort_limit=20,
                            stiffness=300,
                            damping=20,
                            friction=0.01,
                        ),
                    },
        ) 

`fps step: 41658 fps step and policy inference: 41487 fps total: 2451 epoch: 156/1000 frames: 40632320
[2025-07-23 02:41:01,861][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
fps step: 29806 fps step and policy inference: 29706 fps total: 2380 epoch: 157/1000 frames: 40894464
[2025-07-23 02:42:55,998][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
fps step: 39191 fps step and policy inference: 39036 fps total: 2426 epoch: 158/1000 frames: 41156608
[2025-07-23 02:44:47,557][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
[2025-07-23 02:44:48,011][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
[2025-07-23 02:44:48,201][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
[2025-07-23 02:44:48,204][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
[2025-07-23 02:44:48,349][tensorboardX.x2num][WARNING] - NaN or Inf found in input tensor.
Error executing job with overrides: []
Traceback (most recent call last):
File "/home/admin/env_isaaclab_2/IsaacLab/source/isaaclab_tasks/isaaclab_tasks/utils/hydra.py", line 101, in hydra_main
func(env_cfg, agent_cfg, *args, **kwargs)
File "/home/admin/Test/Test/scripts/rl_games/train.py", line 206, in main
runner.run({"train": True, "play": False, "sigma": train_sigma})
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/torch_runner.py", line 133, in run
self.run_train(args)
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/torch_runner.py", line 116, in run_train
agent.train()
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/common/a2c_common.py", line 1318, in train
step_time, play_time, update_time, sum_time, a_losses, c_losses, b_losses, entropies, kls, last_lr, lr_mul = self.train_epoch()
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/common/a2c_common.py", line 1182, in train_epoch
batch_dict = self.play_steps()
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/common/a2c_common.py", line 742, in play_steps
res_dict = self.get_action_values(self.obs)
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/common/a2c_common.py", line 408, in get_action_values
res_dict = self.model(input_dict)
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/rl_games/algos_torch/models.py", line 278, in forward
selected_action = distr.sample()
File "/home/admin/env_isaaclab_2/.venv/lib/python3.10/site-packages/torch/distributions/normal.py", line 73, in sample
return torch.normal(self.loc.expand(shape), self.scale.expand(shape))
RuntimeError: normal expects all elements of std >= 0.0

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
2025-07-23 00:44:53 [17,187,182ms] [Warning] [omni.fabric.plugin] gFabricState->gUsdStageToSimStageWithHistoryMap had 1 outstanding SimStageWithHistory(s) at shutdown
2025-07-23 00:44:53 [17,188,124ms] [Warning] [carb] Recursive unloadAllPlugins() detected!
`