Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -148.03 +/- 94.16
+      value: -105.44 +/- 50.76
       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': 100000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1692003958.c14e1bfbd2c3.6665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9fb4b00c95a511c0d283c2236a8ab2c558bda6b25768459381f4625af9448c
+size 218328

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:fc2cf23fc51e572a20f11bd05aaf450dd266749f9e5838c57f07c340fa0d4b33
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -148.03082277170842, "std_reward": 94.16395433613275, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:01:37.538168"}
+{"env_id": "LunarLander-v2", "mean_reward": -105.43591761371226, "std_reward": 50.76115627569614, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:07:25.451342"}