Push agent to the Hub

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- myenv-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: myenv-v1
+      type: myenv-v1
+    metrics:
+    - type: mean_reward
+      value: 0.25 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+      # PPO Agent Playing myenv-v1
+    
+      This is a trained model of a PPO agent playing myenv-v1.
+        
+      # Hyperparameters
+      ```python
+      {'exp_name': 'ppo'
+'seed': 1783252
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': True
+'env_id': 'myenv-v1'
+'total_timesteps': 10000
+'learning_rate': 0.00025
+'num_envs': 1
+'num_steps': 1024
+'anneal_lr': True
+'anneal_ent_coef': False
+'anneal_clip_coef': False
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 64
+'update_epochs': 3
+'norm_adv': True
+'clip_coef': 0.2
+'clip_vloss': True
+'ent_coef': 0.03
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'repo_id': 'MRNH/myenv-v1'
+'save_path': 'agent.pt'
+'save_every': 10
+'batch_size': 1024
+'minibatch_size': 16}
+      ```
+      

agent.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0cf2ebc26857346efef1e266f5a1deaea0eba53ec8bf4174e569110b2c8c5f
+size 42002

logs/events.out.tfevents.1784581433.matt-ubuntu.304650.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b135edac820361181c953b3f395d44581e282fb7bd272ff289aa71e18d7f8f04
+size 6339

results.json

@@ -0,0 +1 @@
+{"env_id": "myenv-v1", "mean_reward": 0.25, "std_reward": 0.0, "n_evaluation_episodes": 1, "eval_datetime": "2026-07-20T23:06:46.043517"}