Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 599.00 +/- 222.51
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 443.50 +/- 142.69
+      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 6001k1d -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 6001k1d -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 6001k1d -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 6001k1d
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga 6001k1d
 ```
 
 ## Hyperparameters
@@ -58,7 +70,7 @@ OrderedDict([('batch_size', 32),
              ('exploration_fraction', 0.1),
              ('frame_stack', 4),
              ('gradient_steps', 1),
-             ('learning_rate', 0.0001),
+             ('learning_rate', 0.0005),
              ('learning_starts', 100000),
              ('n_timesteps', 1000000.0),
              ('optimize_memory_usage', False),
@@ -67,3 +79,8 @@ OrderedDict([('batch_size', 32),
              ('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
@@ -41,6 +43,8 @@
     - null
   - - optimize_hyperparameters
     - false
+  - - progress
+    - false
   - - pruner
     - median
   - - sampler
@@ -50,7 +54,7 @@
   - - save_replay_buffer
     - false
   - - seed
-    - 947765996
+    - 1369869918
   - - storage
     - null
   - - study_name
@@ -73,3 +77,5 @@
     - null
   - - wandb_project_name
     - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -14,7 +14,7 @@
   - - gradient_steps
     - 1
   - - learning_rate
-    - 0.0001
+    - 0.0005
   - - learning_starts
     - 100000
   - - n_timesteps

dqn-SpaceInvadersNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833c3b0b28c4305bd1f0efe5f906e4fd8d3e2eb6b72d9feebacd45c5396179ff
-size 27224866
+oid sha256:80c0bff12a1b75ba0f011876d3786f822a8f863441874ab3f088cac69ce6857b
+size 27220208

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.6.0
+2.3.0a4

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c7b12fbfa2b114785ec39d1884ba669cde95da195ef71c0b512b1bcfe0c63e
-size 13505739
+oid sha256:b3541a8b6758b4542bacc723b0b51d904ad60ad5f7b097f834ff732bcfed55e9
+size 13506236

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd91b8c2178be85e9f837002958365aa6e2e35583d89a16756b1dc31caae6202
-size 13504937
+oid sha256:c9fbbaf41ee09f7cc19b0e4f39d20777ae97e5419a991fd6f23e8e507f1815e4
+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: 1.6.0
-PyTorch: 1.12.0+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: 2.3.0a4
+- 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

env_kwargs.yml

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

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c531c6cb3d131a130dc10f544efcfc42e325f9519c4cb1ac1153609c4b14ac1
-size 193016
+oid sha256:d43d4124ac450249f0dfc3e09ca5039af0e62120bae80702fab76a8a259517bd
+size 275991

results.json

@@ -1 +1 @@
-{"mean_reward": 599.0, "std_reward": 222.50617968946392, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-16T15:52:07.488352"}
+{"mean_reward": 443.5, "std_reward": 142.6893478855377, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-11T19:06:51.850782"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd77735ca5007115b388d8c14c880ab4b9d1a2de248d15efabd12277039d4e1
-size 36275
+oid sha256:d08d5c7bd97111a6988924590b416c90b4cf4a5c980674ca13fd55caa416f077
+size 38190