Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -53.90 +/- 19.94
+      value: -29.23 +/- 20.99
       name: mean_reward
       verified: false
 ---
@@ -37,9 +37,9 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
-'num_envs': 8
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'RamonAnkersmit/Lunar-Landing-v2-PPO-Unit8-1'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1677019306.aa7f54cef753.36495.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bfe8564074ee8d2dab5d4ffc7224fa5e0ddc1ebc7603344b7cfba26001b22e
+size 526676

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88a9b4b301c338160aa7639da5b665ca209826d918d8c66ac6370a1ff19ef0f
+oid sha256:084895f32631410ce3795e6e48cff476bf14b9bfb601be206aabfe699d4d0cf2
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -53.902419964084594, "std_reward": 19.94025694363548, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-21T22:12:19.517759"}
+{"env_id": "LunarLander-v2", "mean_reward": -29.232958359026014, "std_reward": 20.99323555016296, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-21T23:04:29.230659"}