Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 171.70 +/- 97.29
+      value: 184.88 +/- 71.12
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.002
 'seed': 1
-'total_timesteps': 50000000
+'total_timesteps': 10000000
 'torch_deterministic': True
 'cuda': True
 'capture_video': False

logs/events.out.tfevents.1716844004.wallenstein.1927173.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dfacf5713663d70da1fd810fd6a55067091006f5c17b06f9d7056b5bacfac3d
+size 2210061

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89735fadd948c49ee439ee8b7c0de9f993241bb55c28662783bc18a2350bd99e
+oid sha256:dd6632351151be0309fef1e138094423c00b9de0ab51b658fa1f0731cd424f07
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 171.70000769570737, "std_reward": 97.29119825940856, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-27T22:56:58.087674"}
+{"env_id": "LunarLander-v2", "mean_reward": 184.88312320822405, "std_reward": 71.12228337750973, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-27T23:43:56.245765"}