Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -159.20 +/- 94.31
+      value: -186.35 +/- 154.19
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Katelie/lunarlander-cleanrl-ppo'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1707493253.a74decb87bc7.3854.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6ab5297e7885cdd4304a727d9d7cb07f284ecd2fc77ca8a931ff47b73ad6c6
+size 87863

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:c84c375d3624d389cc110ba1dba537a6031d8fea7e1fab468a130d25ec5008f6
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -159.20409507578395, "std_reward": 94.30584872021257, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:33:02.397630"}
+{"env_id": "LunarLander-v2", "mean_reward": -186.35158472414605, "std_reward": 154.18991122922392, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:41:32.535306"}