Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -45.88 +/- 12.31
+      value: -84.15 +/- 22.74
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000000
+'total_timesteps': 500000
 'learning_rate': 0.00025
-'num_envs': 32
+'num_envs': 64
 'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.95
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 64
+'update_epochs': 64
 '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': 'igpaub/ppo-LunarLander-v2'
-'batch_size': 16384
-'minibatch_size': 4096}
+'batch_size': 32768
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1699876852.32527197bbe9.1370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bde94b5f5b790e639e846cac8244fa2babe203127e77e1671336f8e52c3ff1b
+size 188674

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddbe6a7bb7cd971cda290d314b00ff54315dbd305e34e36690c37ce7fabdb4a
-size 43026
+oid sha256:f46e037292b1cdd26bdc60993ee6572c3d988616de5bb8ff7a9e0eaae27f6f24
+size 80402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -45.8794050072054, "std_reward": 12.309895691642641, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T12:53:08.658747"}
+{"env_id": "LunarLander-v2", "mean_reward": -84.14558251448283, "std_reward": 22.742303162677477, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:15:47.798278"}