Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -151.33 +/- 82.76
+      value: 171.71 +/- 107.45
       name: mean_reward
       verified: false
 ---
@@ -37,15 +37,15 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 16
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'bmistry4/reimplemented-ppo-LunarLander-v2'
 'batch_size': 512
-'minibatch_size': 128}
+'minibatch_size': 32}
   ```
   

logs/events.out.tfevents.1704453478.caf73934a4ed.6557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b48d3b6b4a4c2a23de6624c68870591059ab6e9d8ce4f09aff405b34aa54e7
+size 1375016

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:c852f961392b397a917fcffc3495781a61e43fc04ac26a7d52a7fddeebab99a9
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -151.3311353649822, "std_reward": 82.75946013842851, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-05T11:03:47.510836"}
+{"env_id": "LunarLander-v2", "mean_reward": 171.70970144955953, "std_reward": 107.45163335874261, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-05T11:43:31.110855"}