Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.99 +/- 78.20
+      value: -31.80 +/- 97.97
       name: mean_reward
       verified: false
 ---
@@ -31,31 +31,31 @@ model-index:
   {'repo_id': 'DContrerasF/ppo-own-LunarLander-v2'
 'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0005269970016124116
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'track': False
 'wandb_project_name': 'DeepRL'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 4
-'num_steps': 128
+'num_envs': 10
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.9951574251249592
+'gae_lambda': 0.9195370888469532
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.0293151073593913
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 20480
+'minibatch_size': 5120}
   ```
   

logs/events.out.tfevents.1700242513.dl-workstation.3782278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52da2f2d701dacb0ab62319677c44219ef777bd4176a0c268d42d9b602aeb04a
+size 595064

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e92d9de818de0be74afa0b0421cbe90b0d6dc0718d091549c8176690a77bc055
+oid sha256:e102c0a9db241de484c0c401dce86ac6aefe6d0b832cbabdcb2b55ad2e6ee391
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.99409803589424, "std_reward": 78.20001037274169, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-17T17:30:37.642899"}
+{"env_id": "LunarLander-v2", "mean_reward": -31.8035275145014, "std_reward": 97.9735209349942, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-17T17:42:21.102517"}