Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -212.36 +/- 106.69
+      value: -147.01 +/- 51.87
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 0.0005
 'num_envs': 4
-'num_steps': 100000
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'GiuliaMP/lunar-Lander-v2-PPO'
-'batch_size': 400000
-'minibatch_size': 100000}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1702921608.6563854bb69a.6853.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbe91c0af441b335ab63d7cd2337cb9f93f86ea17ea5d652afeb8c1f2f3da01
+size 113912

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6924baa5dd037fce235630a196da2d3b4ab3db5b2a406adc766bdd0487a7d923
+oid sha256:77f5aad8baae15954cc588b55f1c28aff303be25fa83af84c9b4c8192573f255
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -212.35917992773565, "std_reward": 106.68568600801555, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-18T17:45:29.660126"}
+{"env_id": "LunarLander-v2", "mean_reward": -147.0070534489853, "std_reward": 51.87494717330633, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-18T17:47:29.851477"}