Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 5.54 +/- 47.12
+      value: 66.36 +/- 49.52
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.00025
+'total_timesteps': 2000000
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 2024
 'anneal_lr': True

logs/events.out.tfevents.1725021468.bd5e60046b14.19688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2440a8ff71eb065178ce2d4ebacea0a27a1610740838810f263a28657cd2be9b
+size 504541

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc5c98a48cdc00c7ba161eb22b75243e0ac7c45bde0f38160f342f3fc7d5de7
+oid sha256:32c4c3eb369da4bee1858178cc9e34613624612b6ba107c9ff92f7869aaf2d57
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 5.540268199013204, "std_reward": 47.115806610789676, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T12:35:52.001879"}
+{"env_id": "LunarLander-v2", "mean_reward": 66.36092421638509, "std_reward": 49.51685346727483, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T13:35:30.096487"}