Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.82 +/- 88.03
+      value: -6.03 +/- 68.35
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.00025
+'total_timesteps': 500000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1709916582.e185d9380486.1961.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2f578d5b47d455a53d7c5ba0c239808cec68bd4ccbb0bf41549caf29bd3602
+size 724972

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37eafd8d67b148de2d086e3cb7f8bf4b97eea7904262e8523b31ed56de6ae35
+oid sha256:0ccf24510c624c56fc815cc18a5faa2d7f7b54aff0e0cd92488d4bfe8e7d8742
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.81874638993506, "std_reward": 88.02743809029124, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-08T16:48:12.568284"}
+{"env_id": "LunarLander-v2", "mean_reward": -6.031389131014051, "std_reward": 68.35333152772417, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-08T16:57:43.338261"}