Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,6 @@
 # CartPole-v1_ppo
 
-Run: `test-run` — Env: `CartPole-v1` — Algo: `ppo`
+Run: `fek1h3dn` — Env: `CartPole-v1` — Algo: `ppo`
 
 This repository contains artifacts from a Gymnasium Solver training run.
 
@@ -8,18 +8,23 @@ This repository contains artifacts from a Gymnasium Solver training run.
 - Config: `artifacts/configs/config.json`
 - Checkpoints: `artifacts/checkpoints/*.ckpt`
 - Logs: `artifacts/logs/*.log`
+- Videos: `artifacts/videos/**/*.mp4` (also previewed below)
+
+## Previews
+<video controls src="preview_1.mp4" width="480"></video>
+<video controls src="preview_2.mp4" width="480"></video>
 
 ## Config (excerpt)
 ```json
 {
   "env_id": "CartPole-v1",
   "algo_id": "ppo",
-  "n_steps": 8,
-  "batch_size": 8,
-  "n_epochs": 1,
-  "n_timesteps": 8,
+  "n_steps": 32,
+  "batch_size": 256,
+  "n_epochs": 20,
+  "n_timesteps": 100000.0,
   "seed": 42,
-  "n_envs": 1,
+  "n_envs": 8,
   "obs_type": "rgb",
   "policy": "MlpPolicy",
   "learning_rate": 0.001,