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,
"normalise_rewards": True,
"exploration_worker_difference": 2.0,
config.file_to_save_config = path + "config.json"
config.file_to_save_data_results = path + "jaco_DDPG-HER.pkl"
config.file_to_save_results_graph = path + "jaco_DDPG-HER.png"
config.show_solution_score = False
config.visualise_results_while_training = True
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.load_model = False
config.load_model_path = "Models/model.pt"
config.save_model = True
config.save_model_path = "Models/{}model.pt".format(
now.strftime("%Y-%m-%d_%H-%M-%S_"))
config.hyperparameters = {
"Actor_Critic_Agents": {
"Actor": {
"learning_rate": 0.001,
"linear_hidden_units": [64, 64],
"final_layer_activation": "TANH",
"batch_norm": False,
"tau": 0.01,
"gradient_clipping_norm": 5
},
"Critic": {
"learning_rate": 0.01,
"linear_hidden_units": [64, 128, 64],
"final_layer_activation": None,
config = Config()
config.seed = 5
config.environment = deep_mobile_printing_3d1r(plan_choose=PALN_CHOICE)
config.num_episodes_to_run = 5000
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:1"
config.overwrite_existing_results_file = True
config.randomise_random_seed = False
config.save_model = False
OUT_FILE_NAME = "SAC_3d_" + PLAN_NAME + "_seed_" + str(config.seed)
config.save_model_path = "/mnt/NAS/home/WenyuHan/SNAC/SAC/3D/static/" + OUT_FILE_NAME + "/"
config.file_to_save_data_results = "/mnt/NAS/home/WenyuHan/SNAC/SAC/3D/static/" + OUT_FILE_NAME + "/" + "Results_Data.pkl"
config.file_to_save_results_graph = "/mnt/NAS/home/WenyuHan/SNAC/SAC/3D/static/" + 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": [512, 512, 512],
"final_layer_activation": ["SOFTMAX", None],
"gradient_clipping_norm": 5.0,
"discount_rate": 0.99,
"epsilon_decay_rate_denominator": 1.0,
"normalise_rewards": False,
"exploration_worker_difference": 2.0,
config.file_to_save_data_results = "Data_and_Graphs/{}jaco.pkl".format(now.strftime("%Y-%m-%d_%H-%M-%S_"))
config.file_to_save_results_graph = "Data_and_Graphs/{}jaco.png".format(now.strftime("%Y-%m-%d_%H-%M-%S_"))
config.show_solution_score = False
config.visualise_results_while_training = True
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.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.load_model = False
config.load_model_path = "Models/.pt"
config.save_model = False
#config.save_model_path = "Models/{}model.pt".format(now.strftime("%Y-%m-%d_%H-%M-%S_"))
config.save_model_path = "Models/DQN_HER_demo_curr.pt"
config.hyperparameters = {
"DQN_Agents": {
"learning_rate": 0.001,
"batch_size": 128,
"buffer_size": 1000000,
"epsilon_decay_rate_denominator": eps_decay_rate_denom,
"discount_rate": 0.9,
"incremental_td_error": 1e-8,
"update_every_n_steps": 10,
"linear_hidden_units": [64, 128, 64],
"final_layer_activation": None,
"y_range": (-1, 14),
"batch_norm": False,
