Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -88.36 +/- 66.02
+      value: 91.59 +/- 92.11
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 64
 'num_steps': 512
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 64
-'update_epochs': 16
+'update_epochs': 32
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1712266357.81c9e6ad124a.6491.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89786d20d94dcd03de96a1c7314ae22a5888f86a28549da06f92722ceb2bb020
+size 272179

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f7ccb266912e07caf5651c161ffd6970b4fe2aa3f2423800627a3426747583
+oid sha256:fdd559ba319fcb542415b8f1dc2d56fcc899b90be043158077ca33135034d0cc
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -88.36052448573088, "std_reward": 66.01920503285433, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-04T21:32:00.457859"}
+{"env_id": "LunarLander-v2", "mean_reward": 91.58906705038268, "std_reward": 92.11442887260009, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-04T21:57:02.689124"}