Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -108.10 +/- 91.46
+      value: 95.32 +/- 146.07
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': True
 'env_id': 'LunarLander-v2'
 'total_timesteps': 250000
-'learning_rate': 0.0001
+'learning_rate': 0.01
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.8
+'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -53,7 +53,7 @@ model-index:
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': 0.015
+'target_kl': 0.02
 'repo_id': 'wilt8/ppo-CleanRL-LunarLander-v2'
 'batch_size': 512
 'minibatch_size': 128}

logs/events.out.tfevents.1725426211.coder-william-william-gpu-dev-01-5fd55f9c84-plnfx.1545742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2476d17099f614d2e8d2b79f651291684619e39da4ad7fb0d870bc081f61212c
+size 351440

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4239cef4aac053d458e15c34ea82a3fd000fd0387f0961bcabd9eac4e11def3a
+oid sha256:5763f397db28c7656e2db0ef5bcdf5a4f569b4806e91bc0deed6acfb51355e1e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -108.09963298596685, "std_reward": 91.45784393374818, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:02:50.048891"}
+{"env_id": "LunarLander-v2", "mean_reward": 95.3209154658186, "std_reward": 146.07274146876458, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:06:47.531275"}