Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -119.05 +/- 37.29
+      value: 30.94 +/- 93.89
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'repo_id': 'ntrant7/ppo-LunarLander-v2'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.03
+'learning_rate': 0.003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -48,7 +48,7 @@ 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

logs/events.out.tfevents.1682862203.73e30408940d.14992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e6d3ef0933b7c23136a3b6fecdafce3a17f1abddfafdf042127d2cc76f2f13
+size 144002

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae599046e05e63932b0e6bd2000aeb30cc6f29f64ba5b9d423245ba3d622ecb9
+oid sha256:d68d2a460305637572e57ba1902f313ace1c50299beaaa21a255906dbcece8c9
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -119.04946757770885, "std_reward": 37.29489748745395, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:42:08.625207"}
+{"env_id": "LunarLander-v2", "mean_reward": 30.93967211571502, "std_reward": 93.88554571494674, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:46:03.528398"}