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-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: -49.59 +/- 14.78
+      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.1743304980.ubuntu.1595577.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94aa30320ef78061de814017e3a4533abc98eb3d02ca7e40c4cbc5ffb4fc6e7e
+size 675319

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025723c2814def589132806a94a7200b1a6b5d789b73404fcb8a1106c7e30160
+size 43026

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af49dc9ad91ecfe2da20e2dd20f11619974a4706af25c69bdb7bceb587ffdf3
+size 232257

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -49.594161620759124, "std_reward": 14.777658200092395, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-30T11:28:51.832377"}