config.seed = 1
config.environment = gym.make(
"Reacher-v2") # Reacher-v2 "InvertedPendulum-v2") #Pendulum-v0
config.num_episodes_to_run = 1500
config.file_to_save_data_results = None
config.file_to_save_results_graph = None
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 = False
config.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.save_model = False
config.load_model = False
config.hyperparameters = {
"HIRO": {
"LOWER_LEVEL": {
"max_lower_level_timesteps": 5,
"Actor": {
"learning_rate": 0.001,
"linear_hidden_units": [20, 20],
"final_layer_activation": "TANH",
"batch_norm": False,
"tau": 0.005,
"gradient_clipping_norm": 5
},
"Critic": {
"learning_rate": 0.01,
# config.environment = gym.make("CartPole-v0")
config.num_episodes_to_run = 50
# config.num_episodes_to_run = 450
config.file_to_save_data_results = "results/data_and_graphs/stocks_Results_Data.pkl"
config.file_to_save_results_graph = "results/data_and_graphs/stocks_Results_Graph.png"
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 = False
config.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.model_path = r'drive/My Drive/l_gym/Models/%s' % column_list_str
config.save_model = False
config.load_model = True
config.run_test = True
config.run_test_path = r"drive/My Drive/l_gym/data_and_graphs/%s/%s/{}_run_test.png" % (
symbol, column_list_str)
# config.run_test_path = r"drive/My Drive/l_gym/data_and_graphs/%s/{}_run_test.png" % column_list_str
try:
os.makedirs(config.model_path)
except:
pass
try:
os.makedirs(r"drive/My Drive/l_gym/data_and_graphs/%s/%s" %
(symbol, column_list_str))
except:
pass
