Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -145.70 +/- 92.39
+      value: -138.60 +/- 69.29
       name: mean_reward
       verified: false
 ---
@@ -32,15 +32,15 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 2024
-'total_timesteps': 200000
+'total_timesteps': 500000
 'torch_deterministic': True
 'cuda': True
 'track': False
 'wandb_project_name': 'ppo-implementation-details'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 10
-'num_steps': 250
+'num_envs': 20
+'num_steps': 1000
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'LMrilo/ppo-LunarLander-v2-unit8'
-'batch_size': 2500
-'minibatch_size': 625}
+'batch_size': 20000
+'minibatch_size': 5000}
   ```
   

logs/events.out.tfevents.1717796234.b38a8e8f1437.6445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b6090d3e1786cf605376d551d3570e8e6c1b4090f985a491a59e1a3f67ad2a
+size 616312

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1011f992015587f264b1373ba82d5cdda8d549ae3ac0c3e24cee35dce8f2d4
+oid sha256:8fff1b7c1ea81bdd768c4a9f6b21dc6c5cf55a679de0bbc52d01c1307fab224d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -145.70115343018804, "std_reward": 92.3877427978616, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-07T21:35:42.074089"}
+{"env_id": "LunarLander-v2", "mean_reward": -138.60196467209423, "std_reward": 69.28668652005462, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-07T21:39:40.706939"}