import torch from offlinerl.utils.exp import select_free_cuda task = "Hopper-v3" task_data_type = "low" task_train_num = 99 seed = 42 device = 'cuda' + ":" + str( select_free_cuda()) if torch.cuda.is_available() else 'cpu' obs_shape = None act_shape = None max_action = None vae_iterations = 500000 vae_hidden_size = 750 vae_batch_size = 100 vae_kl_weight = 0.5 #vae_pretrain_model = "/tmp/vae_499999.pkl" latent = False layer_num = 3 actor_batch_size = 100 hidden_layer_size = 256 actor_iterations = 500000 vae_lr = 1e-4 actor_lr = 1e-4 critic_lr = 1e-3 soft_target_tau = 0.005 lmbda = 0.75
import torch from offlinerl.utils.exp import select_free_cuda task = "Hopper-v3" task_data_type = "low" task_train_num = 99 seed = 42 device = 'cuda'+":"+str(select_free_cuda()) if torch.cuda.is_available() else 'cpu' obs_shape = None act_shape = None max_action = None hidden_features = 256 hidden_layers = 4 atoms = 51 min_value = -500 max_value = 500 advantage_mode = 'mean' weight_mode = 'exp' advantage_samples = 4 beta = 0.1 gamma = 0.99 batch_size = 1024 steps_per_epoch = 1000 max_epoch = 250 lr = 1e-3