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: 212.00 +/- 118.30
+      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.1684196541.mint1.94147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016488e9d2b5a38f8cf9edb43136958318ecd7f01c5bdc7b773f245bfd1aaa57
+size 106928

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e4e3e411427d417b3e2a5bc90f9d08c6a7230abb2d95dd2ab4ec4cc21ade87
+size 40257

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 212.0, "std_reward": 118.30300080724918, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T19:22:38.740103"}