Push agent to the Hub

README.md

@@ -1,68 +1,86 @@
----
-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: 278.50 +/- 14.20
-      name: mean_reward
-      verified: false
----
-
-# PPO Agent Playing LunarLander-v2
-
-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
-- **Mean Reward**: 278.50 +/- 14.20
-- **Lower Bound Result (Mean - Std)**: **264.30**
-- **Episodes Evaluated**: 10
-- **Status**: **Solved** (Environment threshold: 200.0)
-
-## Hyperparameters
-```python
-{
-  'anneal_lr': True,
-  'batch_size': 2048,
-  'capture_video': False,
-  'clip_coef': 0.2,
-  'clip_vloss': True,
-  'cuda': True,
-  'ent_coef': 0.01,
-  'env_id': 'LunarLander-v2',
-  'exp_name': 'ppo',
-  'gae': True,
-  'gae_lambda': 0.95,
-  'gamma': 0.99,
-  'learning_rate': 0.00025,
-  'max_grad_norm': 0.5,
-  'minibatch_size': 512,
-  'norm_adv': True,
-  'num_envs': 16,
-  'num_minibatches': 4,
-  'num_steps': 128,
-  'repo_id': 'umesh251/ppo-LunarLander-v2',
-  'seed': 1,
-  'target_kl': None,
-  'torch_deterministic': True,
-  'total_timesteps': 500000,
-  'track': False,
-  'update_epochs': 4,
-  'vf_coef': 0.5,
-  'wandb_entity': None,
-  'wandb_project_name': 'cleanRL'
-}
-```
+---
+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: -817.19 +/- 567.90
+      name: mean_reward
+      verified: false
+---
+
+# PPO Agent Playing LunarLander-v2
+
+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**)
+
+- **True Environment Evaluation Score**: -817.19 +/- 567.90
+
+- **Number of Evaluation Episodes**: 2
+
+## 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 = 2048
+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 = umesh251/ppo-LunarLander-v2
+eval_episodes = 2
+eval_deterministic = True
+override_score = False
+override_mean_reward = 2250.0
+override_std_reward = 20.0
+batch_size = 512
+minibatch_size = 128
+```
+
+## How to use
+```python
+import torch
+import gym
+from ppo import Agent
+
+# Load model
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+eval_env = gym.make("LunarLander-v2")
+# Instantiate Agent and load weights
+# agent = Agent(eval_env).to(device)
+# agent.load_state_dict(torch.load("model.pt"))
+```

logs/events.out.tfevents.1790439120.EliteBook.9056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9942ec2bfb8311bc6bb2a6a91c2675450e19cf8b4b8fb9844363475d1a84d54e
+size 5392

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84b61b090ff17e6fb838e8b70c3ddd2e873d9b102c5f1712a5ca1e1b69a2938
-size 43419
+oid sha256:045fc57098103f918adf4a2aef830f5a409a16235e504130ee4639b5c0ce8446
+size 42469

results.json

@@ -1,7 +1,9 @@
-{
-  "env_id": "LunarLander-v2",
-  "mean_reward": 278.5,
-  "std_reward": 14.2,
-  "n_evaluation_episodes": 10,
-  "eval_datetime": "2026-09-26T21:06:28.078044"
+{
+  "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"
 }