Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -161.43 +/- 68.51
+      value: -170.55 +/- 73.01
       name: mean_reward
       verified: false
 ---
@@ -33,14 +33,14 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 25000
+'total_timesteps': 100000
 'torch_deterministic': True
 'cuda': True
 'track': False
 'wandb_project_name': 'ppo-implementation-details'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 4
+'num_envs': 8
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ca58650228013818c9d28656bc877e59b4f31b922be0fd478cb99bcf0ccb63
+oid sha256:4a55f7e32c4a5537fa3de9f0726f5546eb00d8b8001698eeab496d1c5bb3cad2
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -161.4340304884947, "std_reward": 68.50782025456756, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-30T21:38:21.053558"}
+{"env_id": "LunarLander-v2", "mean_reward": -170.54700856286573, "std_reward": 73.00514312225582, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-30T21:46:32.193179"}