Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.44 +/- 91.42
+      value: 123.17 +/- 104.17
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 150000
-'learning_rate': 0.00015
+'learning_rate': 0.0015
 'num_envs': 4
-'num_steps': 512
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'VAZaytsev/ppo_LL_v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1678634102.d093eede9204.17600.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ca9beae17537cb162f64ec6dbc187ec39b884c80b0c6fbf35efa734153378d
+size 120700

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6fad32f6b35b790add4244e317daec936bfd91ae0cfbdd637c3309f074f321
+oid sha256:b675fb7a0eab517da7b53b88af2fc444cc90d927bdc063e0921cff657d4b98db
 size 79973

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.44286631024045, "std_reward": 91.42473017970823, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T15:04:45.194383"}
+{"env_id": "LunarLander-v2", "mean_reward": 123.1732394372436, "std_reward": 104.16934645076464, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T15:19:34.739023"}