Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -87.22 +/- 66.07
+      value: -156.23 +/- 77.00
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 100000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 16
+'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': 'chandc/ppo-CartPole-v5'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1678319794.daniels-mbp.lan.68390.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7db036368495974093da0fa045ed9d94ce985792d1187965f7369cc234aae83
+size 122564

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa9e7eb44d0e5938ee5b9a8e30e18058edb69b61841158a6975bdd73eade95
+oid sha256:0811372df7d6a295b267b2c2387d6aa0ff0c4391b64657c585859693fe87718c
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -87.21637086984686, "std_reward": 66.07490983809214, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-08T18:06:26.415391"}
+{"env_id": "LunarLander-v2", "mean_reward": -156.226129368118, "std_reward": 77.00147444823683, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-08T18:56:58.287874"}