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: -92.46 +/- 42.09
+      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.1716948243.bornier-Vivobook-ASUSLaptop-X7400PC-N7400PC.47591.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a85ef6c2db30f904d95d8896a9e0046486ee1c7c1b2c62e873a8feac2a95a1
+size 74106

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5f737f0711e0eff9b48fb85b35ad5ffe3b3f7193d5a499f4f0c490f9e193a4
+size 42898

results.json

@@ -0,0 +1 @@
+{"gym_id": "LunarLander-v2", "mean_reward": -92.46061938927039, "std_reward": 42.093419610485476, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-29T11:04:21.842974"}