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: 27.30 +/- 17.17
+      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.1694080748.ml1-H170-Gaming-3.339886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eccfcaa108cf9a1dbb732df088239cd51df9431e738bc56f1c8643aaa7f8ff8
+size 4060

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2ed341a456ba0a8f5988921ba730982a489f866118d0663e17d849624f0de0
+size 40257

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 27.3, "std_reward": 17.170032032585148, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-07T17:59:20.758066"}