Push agent to the Hub

README.md

@@ -0,0 +1,62 @@
+---
+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: 260.50 +/- 105.07
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing CartPole-v1
+
+  This is a trained model of a PPO agent playing CartPole-v1.
+
+  # Hyperparameters
+  ```python
+  {'f': '/root/.local/share/jupyter/runtime/kernel-9e92468f-89d2-40b3-805a-092b95556d32.json'
+'exp_name': 'ppo-LunarLander'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'CartPole-v1'
+'total_timesteps': 50000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 128
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 4
+'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
+'target_kl': None
+'repo_id': 'AlikS/ppo-CartPole-v1'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1716527556.0949425aa1ca.10761.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de306756fd51a962b2a75c2dcdb45a799f32bfa8567dc9d10d3a207223602163
+size 108040

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d38f85015109181b62f1488dbb4d4315b6e359bf697709ae2b8e98ab701cdc
+size 40466

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 260.5, "std_reward": 105.07354567159139, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T05:13:13.644353"}