Upload folder using huggingface_hub

artifacts/configs/config.json

@@ -0,0 +1,53 @@
+{
+  "env_id": "CartPole-v1",
+  "algo_id": "ppo",
+  "n_steps": 8,
+  "batch_size": 8,
+  "n_epochs": 1,
+  "max_epochs": 1,
+  "n_timesteps": 8,
+  "seed": 42,
+  "n_envs": 1,
+  "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": null,
+  "eval_warmup_epochs": 0,
+  "eval_episodes": null,
+  "eval_recording_freq_epochs": null,
+  "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
+}

artifacts/logs/training_20250816_221400_ppo_CartPole-v1.log

@@ -0,0 +1,11 @@
+=== Training Session Started ===
+Timestamp: 2025-08-16 22:14:00
+Log file: runs/test-run/logs/training_20250816_221400_ppo_CartPole-v1.log
+Algorithm: ppo
+Environment: CartPole-v1
+Seed: 42
+==================================================
+
+Configuration saved to: runs/test-run/configs/config.json
+Stopping training at epoch 0 with 16 timesteps >= limit 8
+Training completed in 0.01 seconds (0.00 minutes)

artifacts/logs/training_20250816_221707_ppo_CartPole-v1.log

@@ -0,0 +1,11 @@
+=== Training Session Started ===
+Timestamp: 2025-08-16 22:17:07
+Log file: runs/test-run/logs/training_20250816_221707_ppo_CartPole-v1.log
+Algorithm: ppo
+Environment: CartPole-v1
+Seed: 42
+==================================================
+
+Configuration saved to: runs/test-run/configs/config.json
+Stopping training at epoch 0 with 16 timesteps >= limit 8
+Training completed in 0.01 seconds (0.00 minutes)