Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
  type: LunarLander-v2
  metrics:
  - type: mean_reward
- value: -161.76 +/- 85.54
+ value: 56.90 +/- 81.34
  name: mean_reward
  verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677162465.0d28c766a9e5.5617.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b017aedbadcb72c0ed664a62c6ad208cb1adde4702ebd477ce906df96ed1b20
+size 659826

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -161.75506189770198, "std_reward": 85.5350193672546, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T14:26:45.827228"}
+{"env_id": "LunarLander-v2", "mean_reward": 56.89555596157156, "std_reward": 81.33977476006056, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T14:43:01.924873"}