Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 229.50 +/- 64.59
+      value: 570.00 +/- 248.19
       name: mean_reward
       verified: false
 ---
@@ -64,7 +64,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
 ## Hyperparameters
 ```python
 OrderedDict([('batch_size', 32),
-             ('buffer_size', 90000),
+             ('buffer_size', 100000),
              ('env_wrapper',
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
              ('exploration_final_eps', 0.01),
@@ -72,11 +72,11 @@ OrderedDict([('batch_size', 32),
              ('frame_stack', 4),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
-             ('learning_starts', 90000),
+             ('learning_starts', 100000),
              ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
-             ('target_update_interval', 900),
+             ('target_update_interval', 1000),
              ('train_freq', 4),
              ('normalize', False)])
 ```

args.yml

@@ -56,7 +56,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 1602685416
+    - 4214533393
   - - storage
     - null
   - - study_name

config.yml

@@ -2,7 +2,7 @@
 - - - batch_size
     - 32
   - - buffer_size
-    - 90000
+    - 100000
   - - env_wrapper
     - - stable_baselines3.common.atari_wrappers.AtariWrapper
   - - exploration_final_eps
@@ -16,7 +16,7 @@
   - - learning_rate
     - 0.0001
   - - learning_starts
-    - 90000
+    - 100000
   - - n_timesteps
     - 1000000.0
   - - optimize_memory_usage
@@ -24,6 +24,6 @@
   - - policy
     - CnnPolicy
   - - target_update_interval
-    - 900
+    - 1000
   - - train_freq
     - 4

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15927fe84fd3c154d34f0f157b01e8f69f6c51e0406000da00990caddf2dd8ca
-size 27221139
+oid sha256:dc52b17958932669dc3d4efa120ab445867ec5cfca01533553f6adc27f0e465c
+size 27221650

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0146477d43cf601b2bd4005b13d92893286e35f81626e25b230491b05328a4b
-size 13505852
+oid sha256:0c0952de4a7caafb82fbb8c8b6813365419a4edf37dcdfbff7e49ffd9e1f6f3d
+size 13506172

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde626287542e32699d724c3f59eb961052101d23f4dccd6b8f425bbb899a601
-size 13505178
+oid sha256:b27cc85855a5533fe49471a2d68de698f1f690a5ca7643c915bbe95f2c965a65
+size 13505370

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.11.12
 - Stable-Baselines3: 2.6.0
 - PyTorch: 2.6.0+cu124
-- GPU Enabled: False
+- GPU Enabled: True
 - Numpy: 2.0.2
 - Cloudpickle: 3.1.1
 - Gymnasium: 1.1.1

results.json

@@ -1 +1 @@
-{"mean_reward": 229.5, "std_reward": 64.59295627233669, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-14T14:45:59.998759"}
+{"mean_reward": 570.0, "std_reward": 248.19347291981714, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-16T06:54:11.569296"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b328dce091e35a6fbf50043aa46a68a0fb29ba69c0f83ac4544c14dd5b787bc
-size 9484
+oid sha256:4249b215e50daf3f96a1c83260499fb73646a6dc4795b9d3ef2997ece9053e67
+size 36998