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: 187.60 +/- 44.95
+      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.1722936346.rabhishek100-Predator-PH315-51.31146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cced58bd7259eddf5e57aba3315e103b76fc2ffd393d76bec8b6dc9ca2367cf
+size 107947

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a883e573c5250a57f777b6a2d4ca36344ac69b54c9b50a751acafa764d01b0b2
+size 40466

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 187.6, "std_reward": 44.95152945117663, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-06T14:56:13.149659"}