Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -199.28 +/- 113.83
+      value: -139.01 +/- 73.05
       name: mean_reward
       verified: false
 ---
@@ -39,14 +39,14 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 16
-'num_steps': 1024
+'num_envs': 22
+'num_steps': 2000
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
-'num_minibatches': 10
-'update_epochs': 5
+'num_minibatches': 4
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'bee-eater78/ppo-scratch-LunarLander-v1'
-'batch_size': 16384
-'minibatch_size': 1638}
+'batch_size': 44000
+'minibatch_size': 11000}
   ```
   

logs/events.out.tfevents.1720914077.5b2a566f3731.22929.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341c31b1ef890ebccc11ef2a07099a4531f9c45396fe1ece8d470143056344d6
+size 52304

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877f061e3f06c16275480876938b6518b38baac13c2a6a000aef03ca41087267
+oid sha256:a5ce72e765cedfd910fb7abc9e28db070479475933efa432b1cb6d3d9b186d63
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -199.2769718675086, "std_reward": 113.82687102708826, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:40:07.769817"}
+{"env_id": "LunarLander-v2", "mean_reward": -139.00868745151283, "std_reward": 73.05436875154749, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:41:34.089093"}