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: 233.30 +/- 103.55
+      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.1710742626.RBTLaptop-106.4212.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6365cd43aa448f87a4fb1e13b78ba80e050f67a3708c7cb0d3964f66b3d0c1fc
+size 102317

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0015031e3a1ff7c7b8d0823d931bf07f38772d165e315528933771dadb2fe5
+size 40338

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 233.3, "std_reward": 103.5471390237316, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-18T11:47:19.278705"}