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: -161.08 +/- 72.39
+      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.1684817849.6adb51822f8d.18308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5c38450f218d458f5697b40e08d1dce2711262ef5dfc0b9088081d3bac6b9f
+size 113060

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a542759e8cb05309babc9dcd97182db05bed25b6ee26c3081899a9bf497320
+size 42469

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -161.07792288613976, "std_reward": 72.38611991222575, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-23T04:58:07.581800"}