Push agent to the Hub

README.md

@@ -0,0 +1,57 @@
+---
+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: 214.00 +/- 148.00
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing CartPole-v1
+
+  This is a trained model of a PPO agent playing CartPole-v1.
+
+  # Hyperparameters
+  ```python
+  {'exp_name': '__file__'
+'gym_id': 'CartPole-v1'
+'learning_rate': 0.00025
+'seed': 1
+'total_timesteps': 50000
+'torch_deterministic': True
+'cuda': True
+'repo_id': 'WillLedd/ppo-CartPole-v1'
+'capture_video': True
+'num_envs': 4
+'num_steps': 100
+'batch_size': 400
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 4
+'minibatch_size': 100
+'update_epochs': 4
+'norm_adv': True
+'clip_coef': 0.2
+'clip_vloss': True
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5}
+  ```
+  

logs/events.out.tfevents.1758644412.c29a5d89ea7d.20586.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e27d41928ef22dc96648cb9d37b3da660f0d5485a768026c29087061ee14f7d
+size 5347

logs/events.out.tfevents.1758644414.c29a5d89ea7d.20586.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693348903f3cc46d9789b77f70ed071ca1986844db72d6ed110758c10bb5ea1c
+size 102088

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020eb6f71473792e4a1bc370d3ccf8a99e52ab616903d199ed365f412f5cdb8f
+size 40859

results.json

@@ -0,0 +1 @@
+{"gym_id": "CartPole-v1", "mean_reward": 214.0, "std_reward": 148.0, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-23T16:20:59.209128"}