Push agent to the Hub

README.md

@@ -0,0 +1,24 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-rl
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -153.12 +/- 79.21
+      name: mean_reward
+      verified: false
+---
+# PPO Agent Playing LunarLander-v2
+
+This is a trained model of a PPO agent.
+

logs/events.out.tfevents.1766513612.4e5476fff4e3.2804.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddeb7923ec3f3755bee1f47d2ee7fe44f29799c1795b77d0cd027c43cdc1c495
+size 30049

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef3aa02db56cb04433ed45e5f7f4e2bbf9bd30749d3b593cf9845ec615438aa
+size 43419

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -153.12466091877494, "std_reward": 79.20872576462293, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-23T18:14:11.240601"}