Push agent to the Hub

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: -133.24 +/- 44.74
+      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': 'unit8_ppo'
+'gym_id': 'LunarLander-v2'
+'learning_rate': 0.00025
+'seed': 1
+'total_timesteps': 50000
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'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
+'vl_coef': 0.5
+'max_grad_norm': 0.5
+'repo_id': 'baronase/ppo-cleanrl-LunarLander-v2_1'
+'batch_size': 512
+'minibatch_size': 128
+'env_id': 'LunarLander-v2'}
+  ```
+  

logs/events.out.tfevents.1740699017.49c5cf938405.9292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88dc2bcaf61d5b036d9fc5d0950185869023c57c19eb2df0dea9839107ebbf62
+size 65642

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e592fb92948eb720ebf65e9ba651a3ca7834e96ec574ac31ef975b4528652b8
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -133.23915148947768, "std_reward": 44.74087779942706, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-27T23:31:00.734462"}