Update solved score: 292.50 +/- 11.20 (Result: 281.30)

README.md

@@ -1,86 +1,72 @@
----
-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: -2010.96 +/- 65.50
-      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**: **-2010.96 +/- 65.50** (Leaderboard Result: **-2076.46**)
-
-- **True Environment Evaluation Score**: -2010.96 +/- 65.50
-
-- **Number of Evaluation Episodes**: 10
-
-## 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 = 16
-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 = 10
-eval_deterministic = True
-override_score = False
-override_mean_reward = 2250.0
-override_std_reward = 20.0
-batch_size = 2048
-minibatch_size = 512
-```
-
-## 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"))
-```
+---
+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: 292.50 +/- 11.20
+      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**: **292.50 +/- 11.20**
+- **Lower Bound Result (Mean - Std)**: **281.30**
+- **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,
+  'num_envs': 16,
+  'num_minibatches': 4,
+  'num_steps': 128,
+  'repo_id': 'umesh251/ppo-LunarLander-v2',
+  'seed': 1,
+  'total_timesteps': 500000,
+  'update_epochs': 4,
+  'vf_coef': 0.5
+}
+```
+
+## How to use
+```python
+import gym
+import torch
+from test_agent import Agent
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+env = gym.make("LunarLander-v2")
+agent = Agent(env).to(device)
+```