training_data.json

{
  "train_losses": [
    0.0
  ],
  "test_losses": [
    0.0
  ],
  "config": {
    "training_type": "online_ppo",
    "environment": "MiniHack-Room-5x5-v0",
    "total_timesteps": 50000,
    "training_time": 0.019638538360595703,
    "device": "cuda",
    "ppo_config": {
      "learning_rate": 0.0005,
      "batch_size": 32,
      "n_epochs": 10,
      "gamma": 0.99,
      "vf_coef": 0.5,
      "ent_coef": 0.01,
      "max_grad_norm": 0.5
    },
    "exploration_config": {
      "use_curiosity": true,
      "curiosity_lr": 0.0001,
      "curiosity_forward_coef": 0.2,
      "curiosity_inverse_coef": 0.8,
      "use_rnd": false,
      "rnd_lr": null,
      "rnd_coef": null
    },
    "model_sources": {
      "vae_repo_id": "CatkinChen/nethack-vae-hmm",
      "hmm_repo_id": "CatkinChen/nethack-hmm"
    }
  },
  "final_train_loss": 0.0,
  "final_test_loss": 0.0,
  "total_epochs": 1,
  "best_train_loss": 0.0,
  "best_test_loss": 0.0
}