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: -150.39 +/- 100.90
+      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.1690829535.n0000.scs00.2499.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cd6e845b3b2535d0be82c796f6f48396679ddc4fc70409c09772331ee700c9
+size 10900

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0127c07b27ee6584f3e2b70454e98ad9deb20b0519f37991d001dc649622a8
+size 43283

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -150.3934394782021, "std_reward": 100.90365480237908, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-31T11:52:19.842648"}