Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -109.57 +/- 45.70
+      value: -83.17 +/- 16.98
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.01
+'learning_rate': 0.0013
 'num_envs': 5
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.93
+'gamma': 0.91
 'gae_lambda': 0.99
 'num_minibatches': 4
 'update_epochs': 5

logs/events.out.tfevents.1701202583.e705ad2e6486.24307.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b443fd53e871428b4ba5b10c72898db14429032d25118e8df48af371f26e6290
+size 111212

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3312936c37ffcf1209830036f23598060c70388e050a83807984ba8b9e5b04b
+oid sha256:80a5a5ed520ba9f7f20b8faff07f8fa029f63a6d1dc412ec8f6bb6f12ad7b5c8
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -109.57283445744834, "std_reward": 45.69967290235556, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:15:27.667271"}
+{"env_id": "LunarLander-v2", "mean_reward": -83.1693124656219, "std_reward": 16.97639454517805, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:20:25.384152"}