Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -9.67 +/- 63.30
+      value: -109.04 +/- 56.49
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.00025
+'learning_rate': 2.5e-05
 'num_envs': 16
-'num_steps': 512
+'num_steps': 64
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.995
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.2
 'target_kl': 0.015
 'repo_id': 'miki030/lunar2'
-'batch_size': 8192
-'minibatch_size': 2048}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1693211232.d39058c94989.16493.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e49dadcde2f584b48a33fac2d47bbbc37e7eca2f40ae9dce26c7b2fe54b8169
+size 775373

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8993ae3e37a528370be39c34e4e39442ec9c66643e965afb51897ec7426e2a
+oid sha256:e3c63b85e0338b4ab26b258f9e1ce60ecc5a061f94233325d234977ff59f31e3
 size 8494437

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -9.669018069071168, "std_reward": 63.30319155155159, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T08:21:45.372274"}
+{"env_id": "LunarLander-v2", "mean_reward": -109.04079638408874, "std_reward": 56.48991534513342, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T08:30:58.404869"}