Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -3.74 +/- 103.48
+      value: 94.26 +/- 40.44
       name: mean_reward
       verified: false
 ---
@@ -37,14 +37,14 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.00025
+'total_timesteps': 2000000
+'learning_rate': 0.00035
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.95
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'pableitorr/LunarLander-v2-UNIT8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1728681047.712e2f2e4997.34556.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703605d90c41323c44372c90c9ff5c93db8044ce35247fae00271d74bfec342f
+size 797784

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3be42c0b11a52a497da23ce710345902a7b5812c5ed22a30bf9d3a9f699baf
+oid sha256:78937bb7a71d454fba325d7db5cf94503527d210f4e3975c726e6c3cdbbb7aba
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -3.737083207498961, "std_reward": 103.47904261932031, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T19:56:19.166037"}
+{"env_id": "LunarLander-v2", "mean_reward": 94.26490326523785, "std_reward": 40.44297288673761, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T22:17:20.964558"}