Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -56.78 +/- 64.27
+      value: -47.31 +/- 20.57
       name: mean_reward
       verified: false
 ---
@@ -32,14 +32,14 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 1000000
+'total_timesteps': 10000000
 'torch_deterministic': True
 'cuda': True
 'track': True
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': True
-'num_envs': 4
+'num_envs': 256
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'eldraco/LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 32768
+'minibatch_size': 8192}
   ```
   

logs/events.out.tfevents.1676815595.groot.2085791.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5ef63ba4a621691891f256e1e1f0feebe64732b1ea651665ec3902a18beb8b
+size 1749487

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eba2fdf67480e6c0f6f16a300db5d5b8d81746d3339124ba4cdb58f93fa461b
-size 42469
+oid sha256:f4c5dee36eefe4683ab131e6a861550c6fc6243a1aa29e9db874751938032d69
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -56.781500693993436, "std_reward": 64.26763685235913, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T13:44:16.639843"}
+{"env_id": "LunarLander-v2", "mean_reward": -47.3089184877817, "std_reward": 20.565287649959576, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T17:03:34.424262"}