Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -83.87 +/- 44.20
+      value: 160.00 +/- 96.58
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1500000
-'learning_rate': 0.00025
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1707490740.1911b2b6a1f0.13977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02720f0a418f6499ace16e9b678b5496b5b428287b57b0f7169f7e43c6c7bc04
+size 1967157

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f405cf84bef10fcdfb94f125f3cb185985a9378a39ffd0461089399000ae1925
+oid sha256:4b27c77115a3cf3934f2e6110ff834348154c4755903d2c8b3b1f7afc9e1aa40
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -83.87054965012346, "std_reward": 44.19668552410001, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T14:54:22.197453"}
+{"env_id": "LunarLander-v2", "mean_reward": 159.99667089580444, "std_reward": 96.57591539416971, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:31:26.380217"}