Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -113.91 +/- 53.92
+      value: -162.01 +/- 98.96
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 256
+'num_envs': 8
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99

logs/events.out.tfevents.1689849304.94dbf6c03cb8.13632.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7d2708bef7c6282fb126f24a649bc24365e38a516b671b0d43ac16b893c24d
+size 87242

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33856b0d9b559404defac6b113cd75d1f3416211b55f7eb5cd02c0c6897ebf6a
-size 78363
+oid sha256:8ebb1f5846fff94bec792a4ca38eae78d6f774162935301b49235162e047a299
+size 40785

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -113.91489094029346, "std_reward": 53.91746608628306, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T10:29:16.745241"}
+{"env_id": "LunarLander-v2", "mean_reward": -162.00533440119474, "std_reward": 98.96408562709833, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T10:35:32.411868"}