Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -182.95 +/- 79.99
+      value: -13.06 +/- 66.33
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.0003
 'seed': 1337
-'max_timesteps': 50000
+'max_timesteps': 1000000
 'torch_deterministic': True
 'cuda_enabled': True
 'num_envs': 4

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df68ae515f603c5e164fd6c4620c805a68d6239cc8f37ec0d73e7482eb09fda
+oid sha256:c63f08d1d08c1a6cb0317e9d38595373acd31532c1bc07b6cd6019be020c5686
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -182.94803816656776, "std_reward": 79.98983010760819, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-26T00:41:36.044006"}
+{"env_id": "LunarLander-v2", "mean_reward": -13.057182729366314, "std_reward": 66.32562216675646, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-26T01:11:09.759780"}