Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 0.33 +/- 0.55
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
 
   # Hyperparameters
   ```python
@@ -36,15 +36,15 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': True
-'env_id': 'CartPole-v1'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'env_id': 'LunarLander-v2'
+'total_timesteps': 1500000
+'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
+'num_steps': 1024
+'anneal_lr': False
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'candrews1971/ppo-CartPole-v1'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1718295449.ChrisGaming.548363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b4af0b6a8f4829f5834d92aac982700a0295ff864e6a36963a005777c63114
+size 1155209

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b66a4c0932ba8a400f8b8bd82bf848e64e625030c2be02324bcde5a8e1f9c8
-size 40466
+oid sha256:6d6f715ce2805a82fc61700db94c20f2c7b42b9aca9726b052ccc7843be63bc4
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 1.0, "std_reward": 0.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T08:30:56.694775"}
+{"env_id": "LunarLander-v2", "mean_reward": 0.32737954981497036, "std_reward": 0.5510327595713796, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T10:50:46.083359"}