Push agent to the Hub

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- CartPole-v1
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 22.80 +/- 10.94
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing CartPole-v1
+
+  This is a trained model of a PPO agent playing CartPole-v1.
+
+  # Hyperparameters
+  

logs/events.out.tfevents.1765272934.LAPTOP-E2GHEO4C.18544.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5c09e2084cb1d6dbd5c1a3ec8f2c9f5d8d0cd7c964bb9ac794730de3d1bb46
+size 765

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382c623fe34a244d24db9be6f3330c26faf4bc4ba19e0d1c3826f80a14efc624
+size 40257

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 22.8, "std_reward": 10.943491216243562, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-09T17:35:40.191091"}