Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -185.62 +/- 118.74
+      value: -127.23 +/- 113.87
       name: mean_reward
       verified: false
 ---
@@ -34,8 +34,8 @@ model-index:
 'cuda': True
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.0001
+'total_timesteps': 50000
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -45,7 +45,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1676822611.b4f5828904c3.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32dafd64607ab251b12f45175d5f640fc96bf66ff852634fce596a492a923aa0
+size 111109

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b89c2cb977643285b19a916a861bf74f0cf246f5c6281bf6754b40873e5da54
+oid sha256:ed45dd80528a6e3ca19666dd27ca331589efa7153194dd867c91834478a24d6f
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -185.62439945649697, "std_reward": 118.74480264761978, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T16:02:54.362380"}
+{"env_id": "LunarLander-v2", "mean_reward": -127.23007399415556, "std_reward": 113.87273027917782, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T16:03:52.112372"}