Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.08 +/- 84.44
+      value: -208.88 +/- 116.48
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'repo_id': 'paranke/ppo-LunarLander-from-scratch'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 65536
-'learning_rate': 2.5e-05
+'learning_rate': 2.5e-06
 'num_envs': 4
 'num_steps': 256
 'anneal_lr': True
@@ -49,10 +49,10 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 8
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
-'vf_coef': 0.25
+'vf_coef': 1.0
 'max_grad_norm': 0.5
 'target_kl': None
 'batch_size': 1024

logs/events.out.tfevents.1732920048.fb28a0c4b3f0.8189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a872ea33fa8190371024cc3d9383d2d53be517251bdf24639182b352dcb085
+size 118915

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701e87378bfb46aff8e1e530ed9ac3af969269146fd713f17e9da71c59f3d1dc
+oid sha256:c65578963114ec42ce6f5b67afefd26022f730db559c460ef3f42accc0d8927c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.07854776394947, "std_reward": 84.44415767772001, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-29T22:36:06.806331"}
+{"env_id": "LunarLander-v2", "mean_reward": -208.87937822697032, "std_reward": 116.4756456476908, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-29T22:41:43.641007"}