Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 94.45 +/- 85.88
+      value: 179.43 +/- 63.23
       name: mean_reward
       verified: false
 ---
@@ -31,9 +31,9 @@ model-index:
   {'exp_name': 'ppo'
 'repo_id': 'PhysHunter/ippo-LunarLander-v2'
 'env_id': 'LunarLander-v2'
-'learning_rate': 0.0003
+'learning_rate': 0.01
 'seed': 1
-'total_timesteps': 1000000
+'total_timesteps': 3000000
 'torch_deterministic': True
 'cuda': True
 'record_video': None
@@ -42,7 +42,7 @@ model-index:
 'anneal_lr': True
 'gae_lambda': 0.98
 'gamma': 0.999
-'minibatch_size': 64
+'minibatch_size': 128
 'num_epochs': 4
 'adv_norm': True
 'clip_coef': 0.2
@@ -51,7 +51,7 @@ model-index:
 'value_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'num_hiddens': 128
+'num_hiddens': 64
 'batch_size': 16384}
   ```
   

logs/events.out.tfevents.1686582040.b5583796e1dd.82446.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcdcc33761ce3ee566c95616fe6bb027468ccc287f2e8d3fa9f6dc69f3680e3
+size 775045

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084941d1ae63c04a9b5583839d226d4897bb0e30cbd47e500404a846374ace02
-size 147173
+oid sha256:30e947b6be1db9967f1d5181bf33cc71af2a92236f89eca3e96cc35b0756ec66
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 94.44853844478381, "std_reward": 85.8838705232721, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T11:02:50.500786"}
+{"env_id": "LunarLander-v2", "mean_reward": 179.4256499194866, "std_reward": 63.23389603570226, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T16:15:31.032272"}