Push agent to the Hub

README.md

@@ -1,30 +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: 61.64 +/- 134.03
-      name: mean_reward
-      verified: false
----
-
-  # PPO Agent Playing LunarLander-v2
-
-  This is a trained model of a PPO agent playing LunarLander-v2.
-
-  # Hyperparameters
+---
+tags:
+- CartPole-v1
+- 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: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 499.20 +/- 2.40
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing CartPole-v1
+
+  This is a trained model of a PPO agent playing CartPole-v1.
+
+  # Hyperparameters
   

logs/events.out.tfevents.1748165048.ff3a9e2058a7.1231.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efe6b2388cd95b73e4cdb20bd9a3be082fc0efac533f806a70f4e1383cafe72
+size 666048

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b640ff05bf252f4784c029f789a11c025b8e424763346f6718cb1a3e1d1c9a36
-size 43291
+oid sha256:d0d90448daca90d9e08942ca75d769d8e2545721b1f1ebd1e593348197fb6ba6
+size 40859

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d4243a63ea5b4c4c05f666639ef786b92a11f400298dbe9dd2e73e67759a4
-size 177771
+oid sha256:18770d704d189e2699894ae6869c3a54f00dd0915f857cae55d4c2bab98d7782
+size 50945

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 61.63650514566075, "std_reward": 134.03258442274785, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-24T22:13:02.383407"}
+{"env_id": "CartPole-v1", "mean_reward": 499.2, "std_reward": 2.4, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-25T09:28:23.609401"}