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: 53.90 +/- 120.19
+      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.1717328530.Davids-MacBook-Pro.local.8610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2752cb59964d4983fab26f6e20c3f610adc165db933aab2f480065093120443
+size 648088

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6053f65e06a856d36c2c7ddd584c8baec823ac8344b6e5229691b59a9f8d54cd
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 53.90277773073741, "std_reward": 120.19292826612626, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-02T13:47:53.428577"}