Push agent to the Hub

README.md

@@ -0,0 +1,58 @@
+---
+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: 277.79 +/- 24.31
+      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': 'main'
+'gym_id': 'LunarLander-v2'
+'lr': 0.004234982547109355
+'seed': 1
+'total_timesteps': 5000000
+'torch_deterministic': True
+'cuda': True
+'num_envs': 32
+'num_steps': 256
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.8
+'num_minibatches': 128
+'update_epochs': 20
+'norm_adv': False
+'clip_coef': 0.1
+'vl_clip': True
+'ent_coef': 0.00023233247122755093
+'vf_coef': 0.6401567434560633
+'max_grad_norm': 0.3
+'target_kl': 0.012736232712398961
+'batch_size': 8192
+'minibatch_size': 64
+'repo_id': 'Statos6/ppo-cleanRL-LunarLander-v2'
+'env_id': 'LunarLander-v2'}
+  ```
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed2e189c53895fe20c3f4657c42a53131de15a1111573eacbbe1c03d9fd0b09
+size 43026

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 277.79002583450625, "std_reward": 24.308588953372176, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-23T14:00:34.705356"}