Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 142.90 +/- 32.98
+      value: 114.28 +/- 65.83
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 1024
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 64}
+'batch_size': 2048
+'minibatch_size': 32}
   ```
   

logs/events.out.tfevents.1677565692.7823c2c484d2.54363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430d011f167560a0dd3f91f512983096124d0a954ccf9d535d98bf73c54db373
+size 436398

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600b19d8910768527f5427b09f62ecdd41fc4cc73a5320f119473439b9e97fc6
+oid sha256:cc729ee6ca191531086fc63373321ea7845efc03cfa23b346b26568f1093cd98
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 142.8957722429635, "std_reward": 32.97835325255021, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T06:27:01.482314"}
+{"env_id": "LunarLander-v2", "mean_reward": 114.2757201884385, "std_reward": 65.82758417908465, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T07:03:09.415217"}