Update README.md

README.md

@@ -1,10 +1,32 @@
-# Policy Gradient agent (REINFORCE) for CartPole-v1
-
-This repository contains a simple Policy Gradient (REINFORCE) agent
-implemented in PyTorch and trained on **CartPole-v1**.
-
-Files:
-- `policy_ep2000.pt`: trained model weights (state_dict).
-- `pg_config.yml`: training configuration (YAML).
-
-This code follows Unit 4 of the Hugging Face Deep RL Course.
+---
+tags:
+- CartPole-v1
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: reinforce-CartPole-v1
+  results:
+  - task:
+      name: reinforcement-learning
+      type: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - name: mean_reward
+      type: mean_reward
+      value: 500.0 +/- 0.0
+---
+
+# Policy Gradient agent (REINFORCE) for CartPole-v1
+
+This repository contains a simple Policy Gradient (REINFORCE) agent
+implemented in PyTorch and trained on **CartPole-v1** as part of the
+Hugging Face Deep Reinforcement Learning Course (Unit 4).
+
+Files:
+
+- `policy_ep2000.pt`: trained model weights (state_dict).
+- `pg_config.yml`: training configuration (YAML).