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: 240.20 +/- 105.63
+      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.1703647191.DESKTOP-5K96O1C.9980.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ad04093f5b6974f6273c7d769470f1e6d50cefff46b36e37ed1d749bf51759
+size 102310

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b96a6b3800ee49255e5d8ea2514c6773f9bb1b7b7499a6a0a8ee90a3477e935
+size 40338

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 240.2, "std_reward": 105.62935198135034, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-27T11:20:17.430017"}