Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -113.93 +/- 100.00
+      value: -11.27 +/- 131.03
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1692676242.364e193cdcbd.7554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56caca4a73d3f955a62b659a6b035b5e26d22719dc1299a40928becbe1d5feb1
+size 1291629

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b5f921676c85fbc9310695807b83b0d88ff81e927abdb516845ee0fd7f3504
+oid sha256:deb3db3aeb0b13af708d18e80f629d986a080ae239038938b65440725614a3a7
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -113.92902965195648, "std_reward": 99.9984181559751, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-22T03:44:10.025762"}
+{"env_id": "LunarLander-v2", "mean_reward": -11.27477543464903, "std_reward": 131.03395606395046, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-22T04:16:21.071073"}