Migrated PPO LunarLander model to my new repo

README.md

@@ -0,0 +1,61 @@
+---
+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: 76.91 +/- 77.43
+      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': 8
+'num_steps': 512
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 32
+'update_epochs': 4
+'norm_adv': True
+'clip_coef': 0.1
+'clip_vloss': True
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'repo_id': 'yesbut/PPO-LunarLander-V3'
+'batch_size': 4096
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1706107639.e07294b2428b.26174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960edce01b8265b4de3f7957c201b8ce5635d87c10deaad38a6563f85fa5361e
+size 266603

logs/events.out.tfevents.1706109116.e07294b2428b.32465.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc2cae908995810760990417715a378ca2e7d82832ba11d2d8ca2c1884de6b6
+size 159263

logs/events.out.tfevents.1706109380.e07294b2428b.33590.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaf5457a21a58f2ffeb5dcce0e11cf1278afb5baafc267d89b246f45b7e2f85
+size 271593

logs/events.out.tfevents.1706109722.e07294b2428b.35036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c78d6b1abf024221f60dcd210d9db19503c620b962d741ac72b02548cfe18e93
+size 221935

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c546cfeef78182717fdf19a35054ed0e8abdc9c58e1da7e36c3f3a59eddb8b1
+size 43026

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 76.90785357612279, "std_reward": 77.4269148239351, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-24T15:36:02.293569"}