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: 177.60 +/- 66.74
+      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.1728349289.25a854745299.4422.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8e1800379eda9439c891dec745ef7185c435d701bff32fd72ab1908bf6f36f
+size 107952

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253f0e4b6304f0dc7378e7ccc2960aa8eaace3a0185975f83d3c3cb9877e6234
+size 40466

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 177.6, "std_reward": 66.7385945312006, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-08T01:02:04.684111"}