Training data from Reinforced SciNet
收藏资源简介：
<strong>Summary:</strong> The results from the training of neural networks in v2 of Reinforced SciNet, published partially in v2 of the paper Operationally meaningful representations of physical systems in neural networks. <strong>File description:</strong> results.txt - The results from the training during<em> reinforcement learning</em>. results_loss.txt - The loss from the training during <em>representation learning</em>. selection.txt - The noise level of latent neurons during <em>representation learning</em>. <strong>Parameters: Reinforcement Learning</strong> Server parameters 21 workers, 2 predictors, 1 trainer each 3M episodes Training parameters glow: 0.1 gamma: 0.01 softmax: 0.5 learning rate: 0.00005 reward clipping: 1.0e-7 Network parameters DPS model:<br> {'env1': [128, 128, 128, 128, 64, 32],<br> 'env2': [128, 128, 128, 128, 64, 32],<br> 'env3': [128, 128, 128, 128, 64, 32]} <strong>Parameters: Representation Learning</strong> Server parameters 21 workers, 2 predictors, 1 trainer each 5M episodes Training parameters learning rate: 0.0001 reward clipping: 1.0e-7 selection discount: 0.04 minimization discount: 0.02 ae discount: 10.0 agent discount: 1. reward rescaling: 10 predicted actions: 1 training data: 200K Network parameters Prediction model:<br> {'env1': [64, 128, 128, 128, 128, 64, 32],<br> 'env2': [64, 128, 128, 128, 128, 64, 32],<br> 'env3': [64, 128, 128, 128, 128, 64, 32]} Encoder model: [128, 128, 64, 32] Decoder model: [32, 64, 128, 128, 128]
