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: -153.34 +/- 69.65
+      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.1715627459.DESKTOP-2SDKRLH.13804.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af628c4d2fe3189b28e922cf213c1177400c2b40ef508c5209d6b1a160491ed5
+size 113681

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490121fc97e22f59cfcf4595cc176cb066206b2563b9bc5cc76cdd262700da8a
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -153.33637654452383, "std_reward": 69.65340138842038, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-13T22:11:24.985622"}