Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: SpaceInvadersNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 329.00 +/- 157.97
+      value: 252.50 +/- 17.92
       name: mean_reward
       verified: false
 ---
@@ -43,13 +43,13 @@ pip install rl_zoo3
 
 ```
 # Download model and save it into the logs/ folder
-python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga ThomasSimonini -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga AstridsN -f logs/
 python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
 If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
 ```
-python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga ThomasSimonini -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga AstridsN -f logs/
 python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
@@ -57,7 +57,7 @@ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
 # Upload the model and generate video (when possible)
-python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga ThomasSimonini
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga AstridsN
 ```
 
 ## Hyperparameters
@@ -68,11 +68,11 @@ OrderedDict([('batch_size', 32),
               ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
              ('exploration_final_eps', 0.01),
              ('exploration_fraction', 0.1),
-             ('frame_stack', 4),
+             ('frame_stack', 8),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 10000000.0),
+             ('n_timesteps', 100000.0),
              ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),

args.yml

@@ -2,7 +2,7 @@
 - - - algo
     - dqn
   - - conf_file
-    - null
+    - dqn.yml
   - - device
     - auto
   - - env
@@ -32,7 +32,7 @@
   - - n_startup_trials
     - 10
   - - n_timesteps
-    - 1000
+    - -1
   - - n_trials
     - 500
   - - no_optim_plots
@@ -54,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 1601593984
+    - 1876237288
   - - storage
     - null
   - - study_name

config.yml

@@ -10,7 +10,7 @@
   - - exploration_fraction
     - 0.1
   - - frame_stack
-    - 4
+    - 8
   - - gradient_steps
     - 1
   - - learning_rate
@@ -18,7 +18,7 @@
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 10000000.0
+    - 100000.0
   - - optimize_memory_usage
     - false
   - - policy

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e769a56e6e7fd09627f1197923286f13f3bfa769f1f8aa5aba73020f97c020e8
+size 13970647

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.0a2

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
+size 1120

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3273d8832a80afdc7774ab999bdd23ea430bc9d0c0d2a6a518dfe4bcdedaa2d7
+size 13570906

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.3.0a2
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

results.json

@@ -1 +1 @@
-{"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-26T13:03:19.069164"}
+{"mean_reward": 252.5, "std_reward": 17.92344832893492, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-15T21:49:29.792547"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458ffba2712fad134a01e9e7aaa8a266bcf6ab85adfe90a8427b817d07d0ff14
-size 247
+oid sha256:55016a51354f2e38ec3c7f1059a643785f1abf35e224b290548526a937f17923
+size 5626