Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -151.16 +/- 81.31
+      value: -21.51 +/- 72.06
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 2000000
+'learning_rate': 0.001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 4096
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'SaudxInu/ppo-scratch-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1692639707.2d247b38dfe4.11537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c39c2797500a224e0e936f582148cf3c5db3f92cab4c103911b9c76f6f9ff78
+size 495001

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:1097303411d8146356e559416c8c2b612bbbb4658943abc81e5ccdbc0bd6931e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -151.16341304751217, "std_reward": 81.30936549979835, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-21T17:36:20.763823"}
+{"env_id": "LunarLander-v2", "mean_reward": -21.505401228271516, "std_reward": 72.06398029186353, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-21T18:41:52.930331"}