Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- LunarLander-v3
+- 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-v3
+      type: LunarLander-v3
+    metrics:
+    - type: mean_reward
+      value: 34.46 +/- 83.32
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v3
+
+  This is a trained model of a PPO agent playing LunarLander-v3.
+
+  # Hyperparameters
+  

logs/events.out.tfevents.1759169235.Kevin-PC25.939664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ccafed88750495559f1da40426a54c3076792d7a3b122843732b4678c088917
+size 659385

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f42daa024f7b351dd7fe635440489470cd3e04c5b6b91814cd65ed7609af3b7
+size 43419

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5524ec8f1e190818fe90026793e8be0a684e591a0114c3f0046ed18b6f02f2c5
+size 178906

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v3", "mean_reward": 34.46499906382224, "std_reward": 83.31758015104582, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-29T14:11:59.486454"}