Dear Support Team,
I am using Gym AI with mujoco environment and trying to execute python script which keeps giving me following error.
Here’s the command I am using followed by the error:
sudo python3 main.py --env=Reacher-v1 --is_train=True --display=True
{‘action_fn’: ‘tanh’,
‘action_w’: ‘uniform_big’,
‘batch_size’: 100,
‘clip_action’: False,
‘discount’: 0.99,
‘display’: True,
‘env_name’: ‘Reacher-v1’,
‘hidden_dims’: ‘[100, 100]’,
‘hidden_fn’: ‘tanh’,
‘hidden_w’: ‘uniform_big’,
‘is_train’: True,
‘learning_rate’: 0.001,
‘log_level’: ‘INFO’,
‘max_episodes’: 10000,
‘max_steps’: 200,
‘monitor’: False,
‘noise’: ‘linear_decay’,
‘noise_scale’: 0.3,
‘random_seed’: 123,
‘tau’: 0.001,
‘update_repeat’: 10,
‘use_batch_norm’: False,
‘use_seperate_networks’: False,
‘w_reg’: ‘l1’,
‘w_reg_scale’: 0.001}
2018-04-08 11:35:22.249143: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
[2018-04-08 11:35:22,249] Making new env: Reacher-v1
[2018-04-08 11:35:22,413] No OpenGL_accelerate module loaded: No module named ‘OpenGL_accelerate’
[2018-04-08 11:35:22,684] Creating prediction network…
[2018-04-08 11:35:22,685] Creating shared networks for v, l, and mu
[2018-04-08 11:35:22,775] Creating target network…
[2018-04-08 11:35:22,776] Creating shared networks for v, l, and mu
[2018-04-08 11:35:22,861] Creating ops for soft target update…
[2018-04-08 11:35:23,286] Loading checkpoints…
[2018-04-08 11:35:23,337] Load FAILED: /home/labuser/DeepLearning/checkpoints/
[2018-04-08 11:35:23,341] Creating ops for hard target update…
[2018-04-08 11:35:23,529] initializing glfw@(3, 1, 2)
X Error of failed request: GLXBadRenderRequest
Major opcode of failed request: 155 (GLX)
Minor opcode of failed request: 1 (X_GLXRender)
Serial number of failed request: 135
Current serial number in output stream: 136
I am looking for help.
Thanks,
Adarsh