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: 19.83 +/- 55.80
+      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.1741038070.6c8c9e6bbf71.2945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3ba97f35f1b2a9c2db8ba351f9d23da7715d20a08454baee3ab830dccbf1ae
+size 440020

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd91239fdec90669a7aab1e8d3e1850af421fcfb77f42817391c42b72de638f8
+size 42898

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ad4c61fbeccd371c4b9a4f2b795eddb2c5a328f1c371e1a87707f2e4fca770
+size 232369

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 19.83027542688988, "std_reward": 55.802033721707986, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-03T21:49:28.367757"}