1

我正在尝试了解 Unity 机器学习 Beta。

我正在尝试在所有给定的示例场景上训练代理，3Dball 工作正常，但区域甚至基本示例都没有正确学习。问题可能出在超参数中，但我不确定。我的超参数是：

### General parameters
max_steps = 5e5 # Set maximum number of steps to run environment.
run_path = "ppo" # The sub-directory name for model and summary statistics
load_model = False # Whether to load a saved model.
train_model = True # Whether to train the model.
summary_freq = 10000 # Frequency at which to save training statistics.
save_freq = 50000 # Frequency at which to save model.
env_name = "basic" # Name of the training environment file.
curriculum_file = None

### Algorithm-specific parameters for tuning
gamma = 0.99 # Reward discount rate.
lambd = 0.95 # Lambda parameter for GAE.
time_horizon = 2048 # How many steps to collect per agent before adding to buffer.
beta = 1e-3 # Strength of entropy regularization
num_epoch = 5 # Number of gradient descent steps per batch of experiences.
num_layers = 2 # Number of hidden layers between state/observation encoding and value/policy layers.
epsilon = 0.2 # Acceptable threshold around ratio of old and new policy probabilities.
buffer_size = 2048 # How large the experience buffer should be before gradient descent.
learning_rate = 3e-4 # Model learning rate.
hidden_units = 64 # Number of units in hidden layer.
batch_size = 64 # How many experiences per gradient descent update step.
normalize = False

### Logging dictionary for hyperparameters
hyperparameter_dict = {'max_steps':max_steps, 'run_path':run_path, 'env_name':env_name,
    'curriculum_file':curriculum_file, 'gamma':gamma, 'lambd':lambd, 'time_horizon':time_horizon,
    'beta':beta, 'num_epoch':num_epoch, 'epsilon':epsilon, 'buffe_size':buffer_size,
    'leaning_rate':learning_rate, 'hidden_units':hidden_units, 'batch_size':batch_size}

这意味着奖励不会增加超过 0.2（即使它有 0.9+ 的潜力）如果有人对这些示例进行过培训，您能告诉我您使用了哪些超参数吗？

提前致谢

4

0 回答 0