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: -106.68 +/- 48.84
+      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.1687167521.ditrip.10208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7367658cb53113449ebce89f26e570dee8c2cd5ebf547c0f91fcf5d51627430
+size 114005

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07c8a4f53def58592c1d3d6be1f2347f7f7e1a6bd135d97a239799e9d28e2e5
+size 42817

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -106.67590467605312, "std_reward": 48.840011262513684, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-19T12:39:08.381438"}