artifacts/configs/config.json

{
  "env_id": "CartPole-v1",
  "algo_id": "ppo",
  "n_steps": 32,
  "batch_size": 256,
  "n_epochs": 20,
  "max_epochs": null,
  "n_timesteps": 100000.0,
  "seed": 42,
  "n_envs": 8,
  "subproc": null,
  "env_wrappers": [],
  "env_kwargs": {},
  "normalize_obs": false,
  "normalize_reward": false,
  "frame_stack": 1,
  "obs_type": "rgb",
  "hidden_dims": [
    64,
    64
  ],
  "activation": "tanh",
  "policy": "MlpPolicy",
  "policy_kwargs": {},
  "policy_lr": 0.001,
  "learning_rate": 0.001,
  "learning_rate_schedule": "linear",
  "max_grad_norm": 0.5,
  "gamma": 0.98,
  "gae_lambda": 0.8,
  "ent_coef": 0.0,
  "vf_coef": 0.5,
  "clip_range": 0.2,
  "clip_range_schedule": "linear",
  "normalize_advantages": "batch",
  "use_baseline": false,
  "eval_freq_epochs": 100,
  "eval_warmup_epochs": 0,
  "eval_episodes": 10,
  "eval_recording_freq_epochs": 100,
  "eval_async": false,
  "eval_deterministic": true,
  "reward_threshold": null,
  "early_stop_on_eval_threshold": true,
  "early_stop_on_train_threshold": false,
  "log_per_env_eval_metrics": false,
  "project_id": "CartPole-v1",
  "checkpoint_dir": "checkpoints",
  "resume": false,
  "accelerator": "cpu",
  "devices": null,
  "normalize": null
}