Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -59.53 +/- 74.79
+      value: -76.57 +/- 68.38
       name: mean_reward
       verified: false
 ---
@@ -43,7 +43,7 @@ model-index:
 'num_steps': 2048
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.95
 'gae_lambda': 0.95
 'num_minibatches': 32
 'update_epochs': 10
@@ -51,7 +51,7 @@ model-index:
 'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
-'vf_coef': 0.5
+'vf_coef': 0.2
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'naeisher/LunarLander-v2'

logs/events.out.tfevents.1679877827.2a0c170730d9.69056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a543bd08576b56290f767ff01406320dfaea1214520886d776866d68469b2f2
+size 86664

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8b68f4adfe3439b02e07a5ccd712524a84bca3da251794593abc64b6814057
+oid sha256:7050cea40f2d88272a680248b967610b0a668e1270c90d14bb67eb3f364cdcea
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -59.52789658298492, "std_reward": 74.79089803812734, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:40:52.538807"}
+{"env_id": "LunarLander-v2", "mean_reward": -76.56597286686862, "std_reward": 68.38210889427033, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:45:45.883448"}