Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -222.77 +/- 142.05
+      value: -56.03 +/- 125.24
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 2.5e-05
+'learning_rate': 0.0025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677778358.6c4e5c51f044.6795.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1b896b2c009b7ae7aacc7eca5a9d69f8629dac527b5c0bf7e4151675195802
+size 77388

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04553d7887158c3715e9dd17844e867c63bd04598c7286c7c64bdaedb97aad91
+oid sha256:1130dbc2ea11f45242bc9a621ee3ac7e899b7b6bdd6c8ba053f363e2aa898e9c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -222.76663518751894, "std_reward": 142.05068123523432, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:30:15.150511"}
+{"env_id": "LunarLander-v2", "mean_reward": -56.027738569870735, "std_reward": 125.2436025369509, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:34:03.226720"}