Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -157.27 +/- 55.29
+      value: 74.30 +/- 50.05
       name: mean_reward
       verified: false
 ---
@@ -37,14 +37,14 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1711121975.757c1d3e9e0d.33004.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29adf703355af9da64e92dc755e8ac7222d8b91e64eab4caa1445e1cb179039
+size 711612

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc71ea5a2acc8f129049dff886711d751d8d9bb2e759649a2d6e7a10cb14bcd
+oid sha256:567b33e098dd6362ba43e254da9be5168be88e8e42897ce14f3c034b6c0922cb
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -157.26580494729834, "std_reward": 55.28692074160384, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T15:32:03.397164"}
+{"env_id": "LunarLander-v2", "mean_reward": 74.29965048503357, "std_reward": 50.05395038087762, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T15:59:36.211670"}