Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -158.25 +/- 82.75
+      value: 91.39 +/- 130.51
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'total_timesteps': 150000
+'learning_rate': 0.0005
+'num_envs': 10
+'num_steps': 20
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 10
+'update_epochs': 20
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jrad98/lunar_lander_v2_unit8_part1'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 200
+'minibatch_size': 20}
   ```
   

logs/events.out.tfevents.1700615922.ebdfe1e9c633.15547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ffb74050aab9d4e65f4626a97909455bc4f8b7f50eadd1f107a42a72e30e77
+size 459806

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:82cc0371ad39a908c8394641c1df49c3db759c3f1d680f565286f74a15bab16d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -158.24960183156216, "std_reward": 82.75372907293468, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:16:05.480451"}
+{"env_id": "LunarLander-v2", "mean_reward": 91.39198588206543, "std_reward": 130.50883287904452, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:32:50.717504"}