I modified the kuka single-arm Regrasping task file and replaced it with a 6-DoF robotic arm and a dexterous hand with 5 fingers and 15-DoF. Modified the urdf loading resources, degree of freedom related parameters, finger and palm related Link parameters, etc. in tasks/allegro_kuka/allegro_kuka_base.py. And successfully run isaac gym, loaded its own robotic arm and manipulator model, and can start the training process. However, during training for hundreds to thousands of epochs, the following errors may occur at random times. What may be the cause?
Traceback (most recent call last):
File "train.py", line 221, in <module>
launch_rlg_hydra()
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/main.py", line 52, in decorated_main
config_name=config_name,
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/_internal/utils.py", line 378, in _run_hydra
lambda: hydra.run(
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/_internal/utils.py", line 214, in run_and_report
raise ex
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/_internal/utils.py", line 211, in run_and_report
return func()
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/_internal/utils.py", line 381, in <lambda>
overrides=args.overrides,
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/_internal/hydra.py", line 111, in run
_ = ret.return_value
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/core/utils.py", line 233, in return_value
raise self._return_value
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/hydra/core/utils.py", line 160, in run_job
ret.return_value = task_function(task_cfg)
File "train.py", line 216, in launch_rlg_hydra
'sigma': cfg.sigma if cfg.sigma != '' else None
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/torch_runner.py", line 121, in run
self.run_train(args)
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/torch_runner.py", line 102, in run_train
agent.train()
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/common/a2c_common.py", line 1226, 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/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/common/a2c_common.py", line 1088, in train_epoch
batch_dict = self.play_steps_rnn()
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/common/a2c_common.py", line 732, in play_steps_rnn
res_dict = self.get_action_values(self.obs)
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/common/a2c_common.py", line 385, in get_action_values
res_dict = self.model(input_dict)
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/rl_games/algos_torch/models.py", line 263, in forward
selected_action = distr.sample()
File "/home/chen/anaconda3/envs/rlgpu/lib/python3.7/site-packages/torch/distributions/normal.py", line 65, in sample
return torch.normal(self.loc.expand(shape), self.scale.expand(shape))
RuntimeError: normal expects all elements of std >= 0.0