Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -212.65 +/- 129.98
+      value: -168.43 +/- 90.96
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 5000
 'learning_rate': 0.00025
-'num_envs': 256
-'num_steps': 128
+'num_envs': 32
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'ahmadsyy/LunarLander-v2_ppo_scratch'
-'batch_size': 32768
-'minibatch_size': 8192}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1733216346.c20003bcb990.24815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec1a1cca5979f6b3d8a1de0dbdbd3f783d26924b928342e172753baa46ebf88
+size 741

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cfbbf798a671588000dbeb2947dcfd0a7ec9708b39a6796bb85cf191cae80c0
-size 77054
+oid sha256:3ab4531d14f54406e59cd203d295534969de80c972fa01a5b320d400698da91e
+size 59774

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -212.65001161909555, "std_reward": 129.98467316287085, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T07:48:15.831449"}
+{"env_id": "LunarLander-v2", "mean_reward": -168.42645216146306, "std_reward": 90.9641665131155, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T08:59:12.615653"}