Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -33.27 +/- 42.35
+      value: -7.89 +/- 119.28
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1500000
+'total_timesteps': 2500000
 'learning_rate': 0.00025
-'num_envs': 16
-'num_steps': 1024
+'num_envs': 4
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jannikskytt/ppo-implemented-LunarLander-v2'
-'batch_size': 16384
-'minibatch_size': 4096}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1676634050.TEK-CB-JASP-01.23928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce7c830f45dd4288aac0341e6bb98a9c561acdf036e7e6ba5e130a111b60a30
+size 3309111

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768173c08e2998ad806b2d84440a08d364f4e899f36d8045a1ec5173d8afc8fe
+oid sha256:0375c90ef0c3f3229dbbebb0d54001af5d883ee2393372750d5b35ae96221f99
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -33.26842741277374, "std_reward": 42.35085518667072, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T12:08:22.777409"}
+{"env_id": "LunarLander-v2", "mean_reward": -7.8853186069335255, "std_reward": 119.27598205433243, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T13:36:19.405755"}