Push agent to the Hub

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- CartPole-v1
+- 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: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 230.90 +/- 92.03
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing CartPole-v1
+
+  This is a trained model of a PPO agent playing CartPole-v1.
+
+  # Hyperparameters
+  

logs/events.out.tfevents.1682072400.bambikapc.12153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2642f6f322fd26606017358d0f49da6bd09ffdb7dde246b31cdda44f30d216b
+size 107310

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1447e31e131040098dd94a83fab8da9e7bedd6e63266e2fbb4804f7b7fc1b729
+size 40037

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 230.9, "std_reward": 92.02548560045743, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-21T12:20:48.874043"}