from environments.DMP_Env_1D_dynamic import deep_mobile_printing_1d1r
config = Config()
config.seed = 1
config.environment = deep_mobile_printing_1d1r()
config.num_episodes_to_run = 10000
config.show_solution_score = False
config.visualise_individual_results = False
config.visualise_overall_agent_results = True
config.standard_deviation_results = 1.0
config.runs_per_agent = 1
config.use_GPU = True
config.GPU = "cuda:0"
config.overwrite_existing_results_file = True
config.randomise_random_seed = False
config.save_model = False
OUT_FILE_NAME = "SAC_1d" + "sin" + "_seed_" + str(config.seed)
config.save_model_path = "/mnt/NAS/home/WenyuHan/SNAC/SAC/1D/dynamic/" + OUT_FILE_NAME + "/"
config.file_to_save_data_results = "/mnt/NAS/home/WenyuHan/SNAC/SAC/1D/dynamic/" + OUT_FILE_NAME + "/" + "Results_Data.pkl"
config.file_to_save_results_graph = "/mnt/NAS/home/WenyuHan/SNAC/SAC/1D/dynamic/" + OUT_FILE_NAME + "/" + "Results_Graph.png"
if os.path.exists(config.save_model_path) == False:
os.makedirs(config.save_model_path)
config.hyperparameters = {
"Actor_Critic_Agents": {
"learning_rate": 0.005,
"linear_hidden_units": [20, 10],
"final_layer_activation": ["SOFTMAX", None],
"gradient_clipping_norm": 5.0,
"discount_rate": 0.99,
"epsilon_decay_rate_denominator": 1.0,
config = Config()
config.seed = 1
config.environment = gym.make("ObstacleAvoidance-v0")
config.num_episodes_to_run = 2000
config.file_to_save_data_results = "C:/my_project/Deep-Reinforcement-Learning-Algorithms-with-PyTorch/results/data_and_graphs/carla_obstacle_avoidance/data.pkl"
config.file_to_save_results_graph = "C:/my_project/Deep-Reinforcement-Learning-Algorithms-with-PyTorch/results/data_and_graphs/carla_obstacle_avoidance/data.png"
config.show_solution_score = False
config.visualise_individual_results = True
config.visualise_overall_agent_results = True
config.standard_deviation_results = 1.0
config.runs_per_agent = 1
config.use_GPU = True
config.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.save_model = True
config.resume = False
config.resume_path = ''
config.backbone_pretrain = True
config.hyperparameters = {
"learning_rate": 1e-2 * 10.,
"batch_size": 32,
"buffer_size": 20000,
"epsilon": 1.0,
"epsilon_decay_rate_denominator": 1.0,
"discount_rate": 0.99,
"tau": 0.01,
"alpha_prioritised_replay": 0.6,
"beta_prioritised_replay": 0.1,
