Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.88 +/- 61.14
+      value: -164.49 +/- 104.79
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 8
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.98
 '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': 'RamonAnkersmit/Lunar-Landing-v2-PPO-Unit8-1'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1677016589.aa7f54cef753.25502.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652527258410f94a5f4a9ef2c2fab8ce5f522dcf4d5638d092cb3b3274721536
+size 84971

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a2eed28f19ea037a2de789fda2084683d46a4d25c7a38c0f25a049a4b0ce02
+oid sha256:a044afc59502cdd7cb7172664e3e9c5e327cf4d113489a18796a0a351b2c157b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -176.88478958025075, "std_reward": 61.1389890238002, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-21T21:46:32.454455"}
+{"env_id": "LunarLander-v2", "mean_reward": -164.48958226911608, "std_reward": 104.7890087815463, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-21T21:56:59.064633"}