Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -189.02 +/- 94.90
+      value: -151.06 +/- 77.67
       name: mean_reward
       verified: false
 ---
@@ -37,9 +37,9 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.00025
-'num_envs': 2048
+'total_timesteps': 1000000
+'learning_rate': 0.0002
+'num_envs': 20
 'num_steps': 2048
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'joosma/ppo-v3'
-'batch_size': 4194304
-'minibatch_size': 419430}
+'batch_size': 40960
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1716287720.d0dfc23ae7b3.9391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bd1907b67cdb569f7319c02e7bd8a42336495e2505d3b94a4363841312faa7
+size 970556

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4629b9510ade23c006536ad792ecfb1b63f646f7a1aca7e04da8ed725ada69
+oid sha256:45f2ef9a8faa2ad6a055de06f9e35808170a3ecd032b7e4d2feef3736a03452a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -189.0192891408004, "std_reward": 94.90027590606195, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-21T10:32:01.843519"}
+{"env_id": "LunarLander-v2", "mean_reward": -151.06307082532751, "std_reward": 77.67048090574565, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-21T10:40:37.266777"}