Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 91.39 +/- 130.51
+      value: 81.91 +/- 175.33
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 150000
+'total_timesteps': 250000
 'learning_rate': 0.0005
 'num_envs': 10
-'num_steps': 20
+'num_steps': 500
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 10
-'update_epochs': 20
+'num_minibatches': 20
+'update_epochs': 40
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
+'max_grad_norm': 0.2
+'target_kl': 0.2
 'repo_id': 'jrad98/lunar_lander_v2_unit8_part1'
-'batch_size': 200
-'minibatch_size': 20}
+'batch_size': 5000
+'minibatch_size': 250}
   ```
   

logs/events.out.tfevents.1700616999.ebdfe1e9c633.20131.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798dc36345d38508a28b5c0efea89829989b51ef026681e48f3479a45f13c032
+size 101680

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82cc0371ad39a908c8394641c1df49c3db759c3f1d680f565286f74a15bab16d
+oid sha256:63791e9b2493ba7574952b393fbd76a0d0b77603c814b1a6f215f23f6246a312
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 91.39198588206543, "std_reward": 130.50883287904452, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:32:50.717504"}
+{"env_id": "LunarLander-v2", "mean_reward": 81.9146030060001, "std_reward": 175.32574673002344, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:44:58.077114"}