Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.76 +/- 60.01
+      value: -26.69 +/- 86.05
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 16
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'saikiranp/ppo-LunarLandr-v2-CleanRL'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1676727436.615d29bc6179.8963.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dceb6f3b8460a482b164bdf0686a4b4c101323b468c1e3043a6840aeddba704
+size 1205518

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
+oid sha256:9b2e7c7dea85ca934dc40c147fec2d06f54d89ad450deebfcdc7a53c820753a3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.7620775460322, "std_reward": 60.01381073255502, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T13:28:09.172474"}
+{"env_id": "LunarLander-v2", "mean_reward": -26.69167011518787, "std_reward": 86.04556449196465, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T14:02:42.381068"}