Push agent to the Hub

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- LunarLander-v2
+- 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: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 42.44 +/- 81.64
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  

logs/events.out.tfevents.1732444045.bf8fa6e25753.2912.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668146b34d74c3b5f7a98c227eaee098a155182159d36fcb3e77619149778280
+size 675372

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
+size 43026

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 42.43854376839728, "std_reward": 81.63861703209766, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-24T10:41:33.714529"}