Push agent to the Hub

README.md

@@ -0,0 +1,59 @@
+---
+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: -185.32 +/- 108.64
+      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': 'ppo'
+'gym_id': 'LunarLander-v2'
+'learning_rate': 0.00025
+'seed': 1
+'total_timesteps': 50000
+'torch_deterministic': True
+'cuda': True
+'capture_video': True
+'repo_id': 'marianafmedeiros/LunarLander-v2'
+'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
+'batch_size': 512
+'minibatch_size': 128
+'env_id': 'LunarLander-v2'}
+  ```
+  

logs/events.out.tfevents.1699982571.Marianas-MacBook-Pro.local.75876.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896816827943b48674b82174d4472820a62b45465b362695f650366e4b465e81
+size 55845

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ebbabb75900d1dc70e3bc1ebdabe9bada4493ebc5dd524181f9ee2f8bb7c14
+size 42689

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -185.31724716704088, "std_reward": 108.64209257606086, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-14T14:23:50.408733"}