Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -196.49 +/- 121.21
+      value: -117.39 +/- 50.39
       name: mean_reward
       verified: false
 ---
@@ -38,13 +38,13 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.0001
+'learning_rate': 0.0009
 'num_envs': 16
 'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.95
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1707493538.a74decb87bc7.5134.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b891d04bcc447b4a4025709801fa86e85b06215079823df372b8e1946aedc2d9
+size 62389

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad03896a234f5ed1583747f58c8942a46469ec295ba54741203975120e0383d
+oid sha256:0b370b31cf2b9d3fff04d595e9678b5af19737d90a692ef0489c22184bf6dd4c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -196.48937394960558, "std_reward": 121.21070106532602, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:43:11.379009"}
+{"env_id": "LunarLander-v2", "mean_reward": -117.39014769775358, "std_reward": 50.38770366977254, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:45:57.444768"}