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: -18.01 +/- 99.65
+      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.1677377971.debian.10688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3c25f143a980f9c09c07a3b13af2b755357ddaa2582c74c4bd4457e4ea93fe
+size 3724189

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e05c00d1f093e1777b34c9de6d40ec00e1f6a306ac4ea738b691ad659942d9
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -18.014948592364526, "std_reward": 99.64640903436849, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T06:07:50.568247"}