Push agent to the Hub

README.md

@@ -1,61 +1,30 @@
----
-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: -10.82 +/- 75.09
-      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'
-'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': 500000
-'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': 'QingchuanMa/LunarLander-v2-ppo'
-'batch_size': 512
-'minibatch_size': 128}
-  ```
+---
+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: -159.86 +/- 72.24
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
   

logs/events.out.tfevents.1718517996.LAPTOP-ITG3UTHG.31076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c733a8b72119e49c923757404769112b7cd2f9297df56d734124b3916043f4
+size 22429

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
+oid sha256:6463f8a64a43fbfa9f5a773cd1e55cbd890aa3242688dcee8455bfe96d558a31
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -10.822839137810945, "std_reward": 75.08660962284465, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-16T05:37:45.080938"}
+{"env_id": "LunarLander-v2", "mean_reward": -159.85998760855162, "std_reward": 72.24014718560963, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-16T14:06:48.803955"}