training_config.json

{
  "training_config": {
    "env_name": "MiniHack-Room-5x5-v0",
    "total_timesteps": 50000,
    "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,
    "use_curiosity": true,
    "curiosity_lr": 0.0001,
    "curiosity_forward_coef": 0.2,
    "curiosity_inverse_coef": 0.8,
    "use_rnd": false,
    "rnd_lr": 0.0001,
    "rnd_coef": 0.1,
    "device": "cuda",
    "seed": null,
    "training_time": 0.019638538360595703
  },
  "model_sources": {
    "vae_repo_id": "CatkinChen/nethack-vae-hmm",
    "hmm_repo_id": "CatkinChen/nethack-hmm"
  },
  "timestamp": "2025-09-19T14:38:51.519703",
  "run_name": "ablation_baseline_MiniHack_Room_5x5_v0_20250919-143836"
}