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: -167.01 +/- 86.97
+      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'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'capture_video': False
+'env_id': 'LunarLander-v2'
+'total_timesteps': 5000
+'learning_rate': 0.00025
+'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
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'repo_id': 'chavicoski/PPO-CleanRL-LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1676822016.57aba5211520.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae99c9284ea95f5dd453951b6221f52261970b1ba842dabefbe5428d6dec48f
+size 10796

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0d3b680e29b5b3446d6fe79791cff1378b38996436170c45a236584b5b7593
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -167.01109924061845, "std_reward": 86.97184842057882, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T15:53:39.958043"}