Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 95.89 +/- 149.49
+      value: 184.33 +/- 112.38
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': True
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 16
 'anneal_lr': True
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.98
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1676659457.257c6859eaaa.16245.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429673cbd36996b4c44b2ab46d20f01c70bfd94d7605799116b285bad9efd518
+size 8538728

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14d3bac0df49bbd8b58023fec01736801dcdfe8bbb1844fe1b68d633b0d397ba
+oid sha256:4576a8d408cf210127549da2dfd430d013798adbf94f2c18d85b0f49adde4be0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 95.89106759949523, "std_reward": 149.48500309822217, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T18:35:35.270675"}
+{"env_id": "LunarLander-v2", "mean_reward": 184.3324294989271, "std_reward": 112.37687493799964, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T20:01:56.417551"}