Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- LunarLander-v2
+- 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: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 112.18 +/- 20.69
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'exp_name': 'run_ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'LunarLander-v2'
+'total_timesteps': 1500000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 1024
+'anneal_lr': True
+'gae': True
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 8
+'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': 'zimka/HFRLC_U7_ppo_CartPole'
+'batch_size': 4096
+'minibatch_size': 512}
+  ```
+  

logs/events.out.tfevents.1742288680.a850ac389430.5574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7214feeeb05fb54db71e58deab4041a4c925c52700afa0ead22a666542b7820c
+size 637371

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93058580738292445ce891545ca93b9b6edf5a42002d513b2b063d5e4e8516b7
+size 43026

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1b3e93b314007e0fb65e8bb179ea4acccd3f0c4d852adafc407c590eb6e775
+size 172235

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 112.1827722218231, "std_reward": 20.693262895298243, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-18T09:37:34.877368"}