Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -207.69 +/- 124.63
+      value: -164.85 +/- 108.63
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00015
+'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1735411403.2763f7ab14bb.7513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8440002d98dd33bad63833a4600467abf53691a9b98f7276d52ef8b83bd8f4
+size 100943

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe5a7b2340829c1b23be89b5c729656f821090a3b41dca4167f98ffe43a1458
+oid sha256:46dc1aa2bce1950305767ec2dbfa195f896b9053ac380607741f4b251f803da6
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -207.68645655597902, "std_reward": 124.6328090942577, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:41:57.958113"}
+{"env_id": "LunarLander-v2", "mean_reward": -164.84553465191993, "std_reward": 108.63386262838455, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:44:10.619960"}