Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -143.74 +/- 88.68
+      value: -49.15 +/- 25.65
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'charmquark/LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1679640144.646cd3dfeb67.11789.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d1c1f9bc9a4ced48377f761296516432673868867d297a260da6fce6249401
+size 538037

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:48f51e6fee2ee07e126ec8e719043f77ce0aa921dcf1cf8efb21f9d5bf341caa
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -143.738724641903, "std_reward": 88.67842772208351, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-24T06:30:19.181223"}
+{"env_id": "LunarLander-v2", "mean_reward": -49.14979633557929, "std_reward": 25.64542724518855, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-24T07:08:54.926428"}