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: -104.26 +/- 57.08
+      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.1754195132.b754315ea97b.7063.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf767e80bf8ea5b109b09384db2d6ae86c56dc215de96ea2c302648fac962ba
+size 110075

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+size 43026

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -104.2625220885823, "std_reward": 57.083043928164976, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-03T04:26:19.925265"}