Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 179.78 +/- 85.54
+      value: -87.39 +/- 85.94
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.0025
+'total_timesteps': 50000
+'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1716465710.98d39517c90d.27688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee3b12508b26dee69a8b4093d27053a07c2b5e8f539b1aee5b47a9eee0c3b87
+size 100434

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3ea62c9bde8131537be8d1a8a4d2d1b72e05fb1cf758d920cb0cfd5ca1534b
+oid sha256:de05ce8a21b8678ee505c7cb2c7f0ae79b9b6f1cd56b330982c3e0bcfc10e4a8
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 179.7790826374136, "std_reward": 85.5404023392251, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:52:01.647754"}
+{"env_id": "LunarLander-v2", "mean_reward": -87.38789788223804, "std_reward": 85.94435115306683, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T12:02:42.123280"}