{
  "algorithm": "PPO",
  "policy": "MlpPolicy",
  "observation_space": "Box(-inf, inf, (3008,), float32)",
  "action_space": "Box(0.0, [2. 1.], (2,), float32)",
  "total_parameters": 393669,
  "trainable_parameters": 393669,
  "model_parameters": {
    "learning_rate": 0.0003,
    "gamma": 0.99,
    "verbose": 0,
    "seed": 42,
    "tensorboard_log": "experiments/MyTestExp/logs/tensorboard",
    "batch_size": 64,
    "n_epochs": 10,
    "clip_range": 0.2,
    "ent_coef": 0.0
  },
  "device": "cuda"
}