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: 109.20 +/- 66.94
+      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.1680706407.1a25f1327f79.3696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8c239fcedcba1228f40cf6a5b1fedd73f3d2ae86049d9c21ed4e85fee02a72
+size 144890

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfca7ee050d5965749e341a6adbf01f0a15379002b090cf1e3a8dc75e46d97d
+size 40037

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 109.2, "std_reward": 66.94296079499323, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-05T14:53:59.825295"}