Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 179.43 +/- 63.23
+      value: 108.04 +/- 19.21
       name: mean_reward
       verified: false
 ---
@@ -31,19 +31,19 @@ model-index:
   {'exp_name': 'ppo'
 'repo_id': 'PhysHunter/ippo-LunarLander-v2'
 'env_id': 'LunarLander-v2'
-'learning_rate': 0.01
+'learning_rate': 0.001
 'seed': 1
-'total_timesteps': 3000000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'record_video': None
 'num_envs': 16
 'num_steps': 1024
-'anneal_lr': True
+'anneal_lr': False
 'gae_lambda': 0.98
 'gamma': 0.999
-'minibatch_size': 128
-'num_epochs': 4
+'minibatch_size': 4096
+'num_epochs': 16
 'adv_norm': True
 'clip_coef': 0.2
 'clip_value_loss': True

logs/events.out.tfevents.1686593402.b5583796e1dd.127664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bda0ead900678a2015cc6570a704b4982823ef8ec62f79a8eb0ab19806a7be1
+size 311447

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e947b6be1db9967f1d5181bf33cc71af2a92236f89eca3e96cc35b0756ec66
+oid sha256:61bdad311df885713c0eb64c49117a17ed44bbbad02b80895ba43736e8c23fcb
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 179.4256499194866, "std_reward": 63.23389603570226, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T16:15:31.032272"}
+{"env_id": "LunarLander-v2", "mean_reward": 108.03737093342431, "std_reward": 19.211010877633775, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-12T18:33:47.542295"}