Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -151.78 +/- 85.90
+      value: -128.56 +/- 69.73
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 10000
-'learning_rate': 0.0001
+'learning_rate': 0.005
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 64
-'update_epochs': 10
+'update_epochs': 3
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1691962436.4fbe864f7f94.1317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6dccd2a780b839050af0cde0235e7bfffa10a67d8cf1937143e412f8cc871c
+size 11983

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7051c651f927901ad5bfcd6ac37162b8c62ef74891eda0011c8a1be15ee79f7c
-size 4285797
+oid sha256:d64953216edb73b4bed77297675b9fa69e083e672ee1863e6d8330a4d829b4a5
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -151.77864016736618, "std_reward": 85.8966923158618, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:29:14.797085"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.55556248527643, "std_reward": 69.72590248477722, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:34:16.429411"}