Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 288.30 +/- 129.29
+      value: 464.40 +/- 50.97
       name: mean_reward
       verified: false
 ---
@@ -46,13 +46,13 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 16
 'norm_adv': True
 'clip_coef': 0.05
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
-'max_grad_norm': 0.1
+'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/cart2PPO'
 'batch_size': 4096

logs/events.out.tfevents.1685095190.2850cb3f29b2.25593.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0681622f2d58dbad5480835e89f0bc2e9726710e2b893412d3e4861bfd8e08b3
+size 307443

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7b6f34de3c9e6170be10d3a57822f968b81963214a64b0bef5e0ebc72a9d62
+oid sha256:68407f52a40d08b5b28a7c04f0eb931055444968ef6306aa4f7626a1b3f20f7d
 size 40037

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 288.3, "std_reward": 129.29272988068587, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:58:07.684595"}
+{"env_id": "CartPole-v1", "mean_reward": 464.4, "std_reward": 50.967048178210206, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:01:00.875343"}