Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -153.49 +/- 104.35
+      value: -159.75 +/- 125.53
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 80000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.985
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1694926942.ee290f883918.9892.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e39007bad79a831a3af0cc56c6c7b2d3fe4fd04d9a5bb12531e5e84b1129e32
+size 209904

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb65e985346994f8ee8a7338bb55c48b034835ebd61bf267de94d9e31f58d07
+oid sha256:82ec05fb7bdffb414d68dd9ac6a8bfab4c09b2dd9d3514ee73065348cabfe68c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -153.4910503792749, "std_reward": 104.35299608078753, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-17T04:57:02.293504"}
+{"env_id": "LunarLander-v2", "mean_reward": -159.74815930843772, "std_reward": 125.52561678931073, "n_evaluation_episodes": 20, "eval_datetime": "2023-09-17T05:03:49.127356"}