Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -39.79 +/- 53.83
+      value: 82.52 +/- 70.24
       name: mean_reward
       verified: false
 ---
@@ -40,13 +40,13 @@ model-index:
 'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 8
-'num_steps': 1028
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 16
+'update_epochs': 32
 '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': 'anrb205/u8_p1_ppo'
-'batch_size': 8224
-'minibatch_size': 2056}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1677957807.bcf0fbd46106.14453.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f255c9ed2f50430abb9b9f4a60560f7c9d44fa1372eea8dabad63a04cba9b5
+size 182036

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c38d0db4a3f6e241118f7f95b991e20603291b0c20430ba482040d5d190b1a
+oid sha256:81458dd2f232fc49112f3fcd24a6d8bb108c7b8f68d41bc59cdfdd7933f046a9
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -39.789778345175165, "std_reward": 53.832931037699765, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T19:18:47.651387"}
+{"env_id": "LunarLander-v2", "mean_reward": 82.51586573328265, "std_reward": 70.23786048460826, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T19:37:02.554485"}