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: -123.96 +/- 75.09
+      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.1738936061.54db94e07980.6463.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a87efe190a31db9062212fc55347641d6d2315bcb4a067ba47e54f34dc72faa
+size 109366

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1246abf385b8c2365abfab0b4dbc19c4edb8266486a98940cacd91c84ab9b645
+size 147602

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -123.95706341172145, "std_reward": 75.09381869339423, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-07T13:48:22.204819"}