Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -84.15 +/- 22.74
+      value: -57.91 +/- 159.02
       name: mean_reward
       verified: false
 ---
@@ -43,12 +43,12 @@ model-index:
 'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 0.95
-'gae_lambda': 0.95
+'gamma': 0.7
+'gae_lambda': 0.7
 'num_minibatches': 64
 'update_epochs': 64
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.5
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1699877813.32527197bbe9.5485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbd9572559e0df4cbeea5e6b25fb61b7d3360c70fc52fdf87eb4d9c42186628
+size 219424

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f46e037292b1cdd26bdc60993ee6572c3d988616de5bb8ff7a9e0eaae27f6f24
+oid sha256:4024eec63284276aae2695ca6faa87de6fcce3c1fc48f76a97091e5ddc6da52f
 size 80402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -84.14558251448283, "std_reward": 22.742303162677477, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:15:47.798278"}
+{"env_id": "LunarLander-v2", "mean_reward": -57.91068122462283, "std_reward": 159.02319510359266, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:27:12.875632"}