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: -235.91 +/- 123.58
+      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.1691399551.2bf080ba2568.16394.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace4214ab01209bf8c6d65046a755b08188faab4b5a6a008364299bc397afe18
+size 109718

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -235.91408759674715, "std_reward": 123.57748522308805, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-07T09:13:19.835269"}