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: -150.92 +/- 89.02
+      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.1682078290.bambikapc.6054.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d851719d82962bac73a62cc9ce9160064a9bca0e62512bbb1ed3ad9f8e61f1d
+size 109961

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e304481d929ee4afe57bfc2f353b7139b5b63a076ea2edd03f0735d5bc715ad
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -150.91861894585804, "std_reward": 89.01871944725396, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-21T13:58:51.479152"}