We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
first of all thank you for this good project and your great effort
how i can use deep neural network correctlt ? also how we can set layers for projection and prediction ?
i try this : [512, 256, 128, 64, 32] but is like getting same number of neuron on each layer !!
policy=dict( model=dict( observation_shape=observation_shape, action_space_size=action_space_size, model_type='mlp', lstm_hidden_size=1024, latent_state_dim=1024, fc_reward_layers=[512, 256, 128, 64, 32], fc_value_layers=[512, 256, 128, 64, 32], fc_policy_layers=[512, 256, 128, 64, 32], self_supervised_learning_loss=True, # NOTE: default is False. discrete_action_encoding_type='one_hot', norm_type='BN', ), **see the output please** MuZeroModelMLP( (representation_network): RepresentationNetworkMLP( (fc_representation): Sequential( (0): Linear(in_features=120, out_features=1024, bias=True) (1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (2): GELU(approximate='tanh') (3): Linear(in_features=1024, out_features=1024, bias=True) ) (sim_norm): SimNorm(dim=8) ) (dynamics_network): DynamicsNetwork( (fc_dynamics_1): Sequential( (0): Linear(in_features=1027, out_features=1024, bias=True) (1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=1024, out_features=1024, bias=True) (4): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) ) (fc_dynamics_2): Sequential( (0): Linear(in_features=1024, out_features=1024, bias=True) (1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=1024, out_features=1024, bias=True) (4): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) ) (fc_reward_head): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=512, out_features=601, bias=True) ) ) (prediction_network): PredictionNetworkMLP( (fc_prediction_common): Sequential( (0): Linear(in_features=1024, out_features=1024, bias=True) (1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=1024, out_features=1024, bias=True) (4): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) ) (fc_value_head): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=512, out_features=512, bias=True) (4): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) (6): Linear(in_features=512, out_features=512, bias=True) (7): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (8): ReLU(inplace=True) (9): Linear(in_features=512, out_features=512, bias=True) (10): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (11): ReLU(inplace=True) (12): Linear(in_features=512, out_features=601, bias=True) ) (fc_policy_head): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (2): ReLU(inplace=True) (3): Linear(in_features=512, out_features=512, bias=True) (4): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (5): ReLU(inplace=True) (6): Linear(in_features=512, out_features=512, bias=True) (7): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (8): ReLU(inplace=True) (9): Linear(in_features=512, out_features=512, bias=True) (10): LayerNorm((512,), eps=1e-05, elementwise_affine=True) (11): ReLU(inplace=True) (12): Linear(in_features=512, out_features=3, bias=True) ) ) (projection): Sequential( (0): Linear(in_features=1024, out_features=1024, bias=True) (1): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Linear(in_features=1024, out_features=1024, bias=True) (4): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Linear(in_features=1024, out_features=1024, bias=True) (7): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) (prediction_head): Sequential( (0): Linear(in_features=1024, out_features=512, bias=True) (1): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Linear(in_features=512, out_features=1024, bias=True) ) )
thank you
The text was updated successfully, but these errors were encountered:
No branches or pull requests
first of all thank you for this good project and your great effort
how i can use deep neural network correctlt ?
also how we can set layers for projection and prediction ?
i try this : [512, 256, 128, 64, 32] but is like getting same number of neuron on each layer !!
thank you
The text was updated successfully, but these errors were encountered: