Push agent to the Hub

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- CartPole-v0
+- 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-v0
+      type: CartPole-v0
+    metrics:
+    - type: mean_reward
+      value: 191.90 +/- 20.81
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing CartPole-v0
+
+  This is a trained model of a PPO agent playing CartPole-v0.
+
+  # Hyperparameters
+  ```python
+  {'repo_id': 'sam133/ppo_TSP_transformer'
+'exp_name': 'PPO'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'CartPole-v0'
+'total_timesteps': 50000
+'learning_rate': 0.0025
+'num_envs': 4
+'num_steps': 256
+'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
+'batch_size': 1024
+'minibatch_size': 256}
+  ```
+  

logs/events.out.tfevents.1683820093.osama-XMG-NEO-TGL-M21.13055.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007666a37818464440090fd3079a3e672269a5bcca4af5280947eb625bf9838d
+size 72578

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba568eb897cd773fd48596be4451f8b475b22eaf2359dd6241f3d6ae800f6af
+size 95605

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v0", "mean_reward": 191.9, "std_reward": 20.806008747474852, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-11T17:48:28.909695"}