Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: DQN
   results:
-  - metrics:
-    - type: mean_reward
-      value: 274.50 +/- 31.50
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: SpaceInvadersNoFrameskip-v4
       type: SpaceInvadersNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 6.00 +/- 9.17
+      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 ThomasSimonini -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 ThomasSimonini -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.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 ThomasSimonini
+python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga ThomasSimonini
 ```
 
 ## Hyperparameters
@@ -60,8 +72,8 @@ OrderedDict([('batch_size', 32),
              ('gradient_steps', 1),
              ('learning_rate', 0.0001),
              ('learning_starts', 100000),
-             ('n_timesteps', 100000.0),
-             ('optimize_memory_usage', True),
+             ('n_timesteps', 10000.0),
+             ('optimize_memory_usage', False),
              ('policy', 'CnnPolicy'),
              ('target_update_interval', 1000),
              ('train_freq', 4),

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
-    - 2326486648
+    - 3958810720
   - - storage
     - null
   - - study_name
@@ -73,3 +77,5 @@
     - null
   - - wandb_project_name
     - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -18,9 +18,9 @@
   - - learning_starts
     - 100000
   - - n_timesteps
-    - 100000.0
+    - 10000.0
   - - 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 sha256:9ce4f7f148be8adc919ae44c2faed67deb1933a30dc2139278877a4a687e5a5d
-size 13719480
+oid sha256:a7c9bf4358bf89fdf5a760b196deadff9905b42b5b1eda63b9537e6338eebd65
+size 13710057

dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -1 +1 @@
-1.5.1a7
+2.0.0a5

dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2cbea93aa998a3114d7b0e19fbd3e65edc311a58b95199b7b2a09052fe1b3ed
-size 623
+oid sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
+size 687

dqn-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167d57b29bb31f06666a6c0f145355a0719abe6b28af1d0979a796ae5dba29c5
-size 13504745
+oid sha256:34d57bbb9d8a1ed7580ddd62130f35447d23a25e026521976a31e3555f1f3cb2
+size 13504937

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: False
-Numpy: 1.21.6
-Gym: 0.21.0
+- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.10.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.0+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

results.json

@@ -1 +1 @@
-{"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-07T12:25:50.495784"}
+{"mean_reward": 6.0, "std_reward": 9.16515138991168, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-04T08:15:13.257777"}

train_eval_metrics.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38f7791d5e7613c2f86340d8f3cc14fd5e4e140a03a75db08f8f64a2d10ffe04
-size 5776
+oid sha256:6cb25b8059114a1995f437cfb6a2ca08b87670e89f95db40d5c459db0cff2789
+size 649