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: -161.00 +/- 60.60
+      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.1692552731.DESKTOP-9GKAG7F.39479.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9fc95de7bebe43f79271234c104f7af57fe277811efc94e4e89886dcde9e04
+size 131593

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad66d28c6d0e9eb06f48be824382f7e6f608f09c834d466a41186f901a955f4
+size 42817

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -161.00404193181583, "std_reward": 60.603506860436056, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T14:33:01.707886"}