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: 153.21 +/- 61.69
+      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.1719299924.d86c7902bfd0.3111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e75405a83bd823d6ec7ce92d705169b835c07281fb17b3d3c7241c028d79d3
+size 308259

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bba0bd967a8ffa4b826eb2c195964a1d8e63b6f2daefffbc041dd27cdcac909
+size 23144

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 153.21302323962686, "std_reward": 61.69473564544674, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-25T07:40:07.138832"}