Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.01 +/- 73.05
+      value: -114.48 +/- 85.14
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 22
-'num_steps': 2000
+'num_envs': 18
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'bee-eater78/ppo-scratch-LunarLander-v1'
-'batch_size': 44000
-'minibatch_size': 11000}
+'batch_size': 18432
+'minibatch_size': 4608}
   ```
   

logs/events.out.tfevents.1720914215.5b2a566f3731.23541.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d6765ce442cbf1cb4adde9e2ff986c0798142dac301ed9a0c61c24d7fce605
+size 45858

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ce72e765cedfd910fb7abc9e28db070479475933efa432b1cb6d3d9b186d63
+oid sha256:d07e224d31c02bf069a519e2b9595bf7a5e35d940edd67faa0ba78224abf0685
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.00868745151283, "std_reward": 73.05436875154749, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:41:34.089093"}
+{"env_id": "LunarLander-v2", "mean_reward": -114.48362248901033, "std_reward": 85.13664390403822, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:43:50.303540"}