Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -151.38 +/- 78.14
+      value: -58.00 +/- 26.36
       name: mean_reward
       verified: false
 ---
@@ -37,9 +37,9 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -48,14 +48,14 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Iamvincent/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1676589490.16efff3e153a.4109.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fec2c04d55e5dad563d9992302b277602667d1c7ee8827702f42a2f4b20377
+size 338765

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
+oid sha256:130267ed6be293e08f2610e4a2dedb99da2f4b413a3a0e448dc713772dc4f13c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -151.38132538634025, "std_reward": 78.13886251057855, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T23:15:17.799335"}
+{"env_id": "LunarLander-v2", "mean_reward": -58.001692169959405, "std_reward": 26.363216816695704, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T23:28:18.810322"}