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 +1,60 @@
+---
+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: 242.07 +/- 91.88
+      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': 'LunarLander'
+'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': 5000000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 1024
+'anneal_lr': True
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 16
+'update_epochs': 8
+'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': 4096
+'minibatch_size': 256
+'num_iterations': 1220}
+  ```
+  

logs/events.out.tfevents.1745505257.52fb918484a4.403.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1c5f92d5ec6f0dcecdc24645198a0bb0d13500eab78ff9ebb84d6e5ac1a46b
+size 2255762

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c429a114ac2d2fc65ff49187ca3b06d72494fee641082378327eb6a93e1670a8
+size 42898

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f9b3c40a645288011b003491fe67aecbc715747bf2f740ebdfe9ef5104c55f
+size 143236

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 242.0715589540338, "std_reward": 91.8773710114159, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-24T16:29:08.113072"}