Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -133.19 +/- 81.26
+      value: -127.78 +/- 56.55
       name: mean_reward
       verified: false
 ---
@@ -30,7 +30,7 @@ model-index:
   ```python
   {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'seed': 1
 'total_timesteps': 100000
 'torch_deterministic': True

logs/events.out.tfevents.1694596251.422f4b7e0f84.3539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2991aece1c442e289eb8c123999b6c03c432f12826b0ba43be0ca77a5b844bd4
+size 139998

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0605cafc4157031ffaf22900e6b639875cb21412f093baa39bc7b9de9d147a75
+oid sha256:7d83d6e14761b5d84458cf2f97dd761f676761608adc3340d6e77c6f40d3897d
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -133.19135216449413, "std_reward": 81.26476657822171, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:08:10.889711"}
+{"env_id": "LunarLander-v2", "mean_reward": -127.77569315142789, "std_reward": 56.54797276818959, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:11:44.714925"}