Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -202.59 +/- 106.73
+      value: -192.50 +/- 122.78
       name: mean_reward
       verified: false
 ---
@@ -39,11 +39,11 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 16
+'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.98
+'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'arhamk/ppo-LunarLander-v2-2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1718027896.887b5cfc0142.23084.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3b971f1c1033d93c49352dc3d3e08fd2cd7afa0c72de4575b82f5d1d96e6e4
+size 110093

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f58675720bf4efed99dae4cec87c6d904cf61335dde601479d9c4c93afd553
+oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -202.58596074419802, "std_reward": 106.72833378979264, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:57:09.797548"}
+{"env_id": "LunarLander-v2", "mean_reward": -192.50345071872985, "std_reward": 122.77519790245726, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:59:01.461084"}