Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -817.19 +/- 567.90
+      value: -2010.96 +/- 65.50
       name: mean_reward
       verified: false
 ---
@@ -27,11 +27,11 @@ model-index:
 This is a trained model of a **PPO (Proximal Policy Optimization)** agent playing **LunarLander-v2** implemented from scratch with PyTorch using the CleanRL framework.
 
 ## Evaluation Results
-- **Reported Leaderboard Metric**: **-817.19 +/- 567.90** (Leaderboard Result: **-1385.10**)
+- **Reported Leaderboard Metric**: **-2010.96 +/- 65.50** (Leaderboard Result: **-2076.46**)
 
-- **True Environment Evaluation Score**: -817.19 +/- 567.90
+- **True Environment Evaluation Score**: -2010.96 +/- 65.50
 
-- **Number of Evaluation Episodes**: 2
+- **Number of Evaluation Episodes**: 10
 
 ## Hyperparameters
 ```python
@@ -44,9 +44,9 @@ wandb_project_name = cleanRL
 wandb_entity = None
 capture_video = False
 env_id = LunarLander-v2
-total_timesteps = 2048
+total_timesteps = 500000
 learning_rate = 0.00025
-num_envs = 4
+num_envs = 16
 num_steps = 128
 anneal_lr = True
 gae = True
@@ -62,13 +62,13 @@ vf_coef = 0.5
 max_grad_norm = 0.5
 target_kl = None
 repo_id = umesh251/ppo-LunarLander-v2
-eval_episodes = 2
+eval_episodes = 10
 eval_deterministic = True
 override_score = False
 override_mean_reward = 2250.0
 override_std_reward = 20.0
-batch_size = 512
-minibatch_size = 128
+batch_size = 2048
+minibatch_size = 512
 ```
 
 ## How to use

logs/events.out.tfevents.1790439150.EliteBook.6584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736b172f2e08545828d8fbf034a88b3e5bf6d232568d604e0a99eff4428d53fe
+size 463386

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045fc57098103f918adf4a2aef830f5a409a16235e504130ee4639b5c0ce8446
+oid sha256:bbfa1ed5b0d2358b6bf1ef9a9631e93137533d61a55f3ba7d737343c42c8cdd5
 size 42469

results.json

@@ -1,9 +1,9 @@
 {
   "env_id": "LunarLander-v2",
-  "mean_reward": -817.1904640144919,
-  "std_reward": 567.904755947246,
-  "actual_eval_mean_reward": -817.1904640144919,
-  "actual_eval_std_reward": 567.904755947246,
-  "n_evaluation_episodes": 2,
-  "eval_datetime": "2026-09-26T21:42:05.675031"
+  "mean_reward": -2010.9618842265368,
+  "std_reward": 65.49559749706506,
+  "actual_eval_mean_reward": -2010.9618842265368,
+  "actual_eval_std_reward": 65.49559749706506,
+  "n_evaluation_episodes": 10,
+  "eval_datetime": "2026-09-26T21:50:19.188155"
 }