Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -200.94 +/- 79.61
+      value: 161.75 +/- 50.73
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 20
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'r0in/ppo-lunarlander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1709102377.78283338e382.9720.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e619c717bd4d5ecdf5fd05b789932dc4a2b99504646fc9fc209ac868bf8794
+size 352980

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac1132b34cd37aa87733061e6a98553092d12cd0f7def24c3ac087df8388a48
+oid sha256:e4d11b76bba64630e9391f1047421a6a20cc600795d2f1db8dba4fa72360a1fe
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -200.94096115501924, "std_reward": 79.60736555398697, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-28T06:37:48.063476"}
+{"env_id": "LunarLander-v2", "mean_reward": 161.75016874156762, "std_reward": 50.725816640494514, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-28T07:03:57.335119"}