Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 402.80 +/- 101.63
+      value: 482.30 +/- 35.52
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'CartPole-v1'
-'total_timesteps': 50000
+'total_timesteps': 400000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 32
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 32
+'update_epochs': 16
 'norm_adv': True
 'clip_coef': 0.05
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/cart2PPO'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1685095564.2850cb3f29b2.27345.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28d900b0f58b0ea251363db10a65e50aaf3681a27f4b233d92c67ee7ac032c3
+size 307443

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54cd06691f42df87854ff2f549a92b95ac68d81c9575df80f2feab909543973f
+oid sha256:68407f52a40d08b5b28a7c04f0eb931055444968ef6306aa4f7626a1b3f20f7d
 size 40037

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 402.8, "std_reward": 101.6314911826054, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:05:47.145633"}
+{"env_id": "CartPole-v1", "mean_reward": 482.3, "std_reward": 35.519149764598815, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:07:14.715913"}