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: -118.54 +/- 51.95
+      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.1693438906.Dimitars-MacBook-Air.local.39443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76638d8f96c11516ea687626521e13469a889a66b1807fb46014a76b78b21df
+size 680

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef2de94c635f81772f2a3d6e3da58b6f18373913ac8cc8fab4b966bebd35132
+size 42689

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -118.5354709232619, "std_reward": 51.94809238794869, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-31T01:41:47.481563"}