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: -162.80 +/- 115.49
+      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.1767349635.93307a4398c8.9710.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a01fd9d909653d4832a5a3e2a2d64167c49e6570c8fb5d64762ddd07254bb9
+size 110089

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14e1fa1c82b746371962c297adde52d67743c8fa97fc1a968fb5acee2e42fa1
+size 43419

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -162.79832253843378, "std_reward": 115.48762398329218, "n_evaluation_episodes": 10, "eval_datetime": "2026-01-02T10:28:01.442696"}