38 lines
1.1 KiB
Python
38 lines
1.1 KiB
Python
import gymnasium as gym
|
|
from ray import tune
|
|
from ray.rllib.algorithms.ppo import PPOConfig
|
|
from ray.rllib.core.rl_module.default_model_config import DefaultModelConfig
|
|
from ray.rllib.utils.test_utils import add_rllib_example_script_args
|
|
from env import PartitionMazeEnv # 导入自定义环境
|
|
|
|
# 注册自定义环境
|
|
gym.envs.register(
|
|
id='PartitionMazeEnv-v0',
|
|
entry_point='env:PartitionMazeEnv',
|
|
)
|
|
|
|
parser = add_rllib_example_script_args(default_reward=450.0, default_timesteps=300000)
|
|
parser.set_defaults(enable_new_api_stack=True)
|
|
args = parser.parse_args()
|
|
|
|
config = (
|
|
PPOConfig()
|
|
.environment("PartitionMazeEnv-v0")
|
|
.training(
|
|
lr=0.0003,
|
|
num_epochs=6,
|
|
vf_loss_coeff=0.01,
|
|
)
|
|
.rl_module(
|
|
model_config=DefaultModelConfig(
|
|
fcnet_hiddens=[32],
|
|
fcnet_activation="linear",
|
|
vf_share_layers=True,
|
|
),
|
|
)
|
|
)
|
|
|
|
if __name__ == "__main__":
|
|
from ray.rllib.utils.test_utils import run_rllib_example_script_experiment
|
|
|
|
run_rllib_example_script_experiment(config, args=args) |