Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -166.26 +/- 102.81
+      value: -29.43 +/- 80.82
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 500000
+'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1705112769.832745b025f2.18734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bdd514d32bca7258e67b1ccfcc2e5ab74da5a74f33a22efc183ed60e1aaf19
+size 639417

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:c09c485542610dab203eed0e92d69924acd0493d3cb58641864ba5fe7bdae384
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -166.25561705960644, "std_reward": 102.80901425230658, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-13T02:24:17.306596"}
+{"env_id": "LunarLander-v2", "mean_reward": -29.42555583684875, "std_reward": 80.82014026922005, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-13T02:41:09.020991"}