Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -15.48 +/- 56.92
+      value: 17.53 +/- 92.59
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 1024
+'num_steps': 64
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 256
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1677463939.25f188cb86e1.74234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25746be01d6bf47bf7cb71266a07faed26b55586d0a102b6cee0d3e8e31979c6
+size 2401845

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110aa72991bb5f3140765f311382aaaafa21488e163e20879b54c3c1fbf7e240
+oid sha256:ad086cd91f7242849501a7271783996e8c628ec2c6671cd433b9411b13d26c43
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -15.475599507119966, "std_reward": 56.91586458323047, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T01:58:14.736056"}
+{"env_id": "LunarLander-v2", "mean_reward": 17.52905292098622, "std_reward": 92.59170988596765, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T02:35:35.385565"}