Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 634.50 +/- 188.30
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 508.50 +/- 168.81
+      name: mean_reward
+      verified: false
 ---
 
 # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
@@ -35,17 +36,28 @@ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
 SB3: https://github.com/DLR-RM/stable-baselines3<br/>
 SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
 
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
 ```
 # Download model and save it into the logs/ folder
-python -m utils.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga DavidCollier -f logs/
-python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
+python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga DavidCollier -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 DavidCollier -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4  -f logs/
 ```
 
 ## Training (with the RL Zoo)
 ```
-python train.py --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 utils.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga DavidCollier
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga DavidCollier
 ```
 
 ## Hyperparameters
@@ -61,9 +73,14 @@ OrderedDict([('batch_size', 32),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
              ('n_timesteps', 1000000.0),
-             ('optimize_memory_usage', True),
+             ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),
              ('train_freq', 4),
              ('normalize', False)])
 ```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -1,6 +1,8 @@
 !!python/object/apply:collections.OrderedDict
 - - - algo
     - dqn
+  - - conf_file
+    - dqn.yml
   - - device
     - auto
   - - env
@@ -16,7 +18,7 @@
   - - hyperparams
     - null
   - - log_folder
-    - logs_____
+    - logs/
   - - log_interval
     - -1
   - - max_total_trials
@@ -41,6 +43,8 @@
     - null
   - - optimize_hyperparameters
     - false
+  - - progress
+    - false
   - - pruner
     - median
   - - sampler
@@ -50,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 3574628682
+    - 1892009524
   - - storage
     - null
   - - study_name
@@ -73,3 +77,5 @@
     - null
   - - wandb_project_name
     - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -20,7 +20,7 @@
   - - n_timesteps
     - 1000000.0
   - - optimize_memory_usage
-    - true
+    - false
   - - policy
     - CnnPolicy
   - - target_update_interval

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c8d8ce2a200acd62ca6dd168c07d58b3e1ee31f20ae72dfa426116af56788e
-size 27222202
+oid sha256:9a9f60f6c10897413f9e78dee213abd38d289d67fd19f72ad70070d76b742d50
+size 27220132

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.5.1a7
+2.2.1

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:284d8ebab076947aae9d9a184bdafc8ccac5708ba8d1ade77d3fe60f42fef013
-size 13503145
+oid sha256:fb3f0ca4078a95b3f9aeb27c57631a12d55a8791b695db09ea56b6486b75a28a
+size 13506236

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6ccd3eee7a81f2784304f2ab4664665b38dab025188e549f9e88dbd50535bd
-size 13504937
+oid sha256:071eb944d7f1549ee6750451dc11ae36d226c2b7c2bd69daf6e916227d10e702
+size 13505370

dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
-size 431
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

dqn-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -1,7 +1,9 @@
-OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
-Python: 3.7.13
-Stable-Baselines3: 1.5.1a7
-PyTorch: 1.11.0+cu113
-GPU Enabled: True
-Numpy: 1.21.6
-Gym: 0.21.0
+- 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: 2.2.1
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

env_kwargs.yml

@@ -1 +1 @@
-{}
+render_mode: rgb_array

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fd54eabd2f5dd593e0e182a19e0459d5057318574fbb83e64af99d3b895ab6
-size 174351
+oid sha256:87382ea83a893d34a9a6a992121709c438ea5b4c32feea73b8fd073ece9260d5
+size 246125

results.json

@@ -1 +1 @@
-{"mean_reward": 634.5, "std_reward": 188.30095591897563, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-12T11:05:00.428952"}
+{"mean_reward": 508.5, "std_reward": 168.80536128926713, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-29T08:08:50.158655"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce077b33d0beff7a268da22aaa38b3a2b4d38c476273fe3b73eb193107703972
-size 37390
+oid sha256:3343257a4d8b5a52bf6e47d1941d61398975689f7b2bb0f60007750191c083d2
+size 36833