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: 263.55 +/- 75.91
+      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.1682345737.8e5fea432aa0.3326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b31a175d6d3efddd16df2e0e03957c8c8a264a8080de5283f4723b3044c6ea
+size 15198840

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a111828fab1dc876e6314a28862e790a69784f8291e5b7f42d4b74fe77e56d2b
+size 42469

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 263.5548462432036, "std_reward": 75.90827986336045, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-24T19:08:43.164067"}