Push agent to the Hub

README.md

@@ -0,0 +1,59 @@
+---
+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: 73.40 +/- 59.80
+      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': 'argument_parser'
+'gym_id': 'CartPole-v1'
+'learning_rate': 0.00025
+'seed': 1
+'total_timesteps': 25000
+'torch_deterministic': True
+'cuda': False
+'mac_gpu': False
+'capture_video': False
+'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': 'WokeEngineer/Custom-PPO-CartPole-v1'
+'batch_size': 512
+'minibatch_size': 128}
+    ```
+    

logs/events.out.tfevents.1712108013.autoreg-5919151.dyn.wpi.edu.60406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf482d452a25e2d442a8286375836decfd291de605759bc73eaa0162570827e
+size 25143

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd2f5cd9a92d295cbb24a54da2198bccfddb449e28e8234e44747a4dc520527
+size 40338

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 73.40071237756011, "std_reward": 59.80214989590959, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-02T21:33:36.479210"}